[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6990ZD8M3PRBXD8DAH82DA1":3,"skill-same:01M6990ZD8M3PRBXD8DAH82DA1":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6990ZD8M3PRBXD8DAH82DA1","mantis-launch",null,"Launches automated vulnerability review campaigns on target files or repositories. Use to initiate Mantis vulnerability review pipelines with automated preflight checks, environment auto-configuration, and runtime overrides (sandboxes, models, endpoints). Don't use for configuring settings without scanning or for manual single-stage reviews.","google\u002Fmantis","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M6990SDGGFEAP21TJNS7HEG9",2773,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Freference\u002Fskills\u002Fmantis-launch\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"mantis launch","launch","repositories","review","single","for","initiate","manual","reviews","sandboxes","with","runtime","stage","campaigns","endpoints","files","scanning","auto","use","environment","preflight","vulnerability","2026-11-10 10:12:30",false,"---\nname: mantis-launch\ndescription: >-\n  Launches automated vulnerability review campaigns on target files or repositories.\n  Use to initiate Mantis vulnerability review pipelines with automated preflight checks, environment auto-configuration, and runtime overrides (sandboxes, models, endpoints).\n  Don't use for configuring settings without scanning or for manual single-stage reviews.\n---\n\n# Campaign Launcher (\u002Fmantis-launch)\n\n## System Goal\n\nAutonomous Security Review Pipeline Launcher. Initiates end-to-end vulnerability\ndiscovery, independent verification, exploit viability analysis, crash\nreproduction, automated patch generation, and risk calibration campaigns across\na target file or entire codebase repository.\n\nAutomatically detects unconfigured environment placeholders (such as\n`YOUR_PROJECT_ID` in GCE sandboxes), auto-resolves active credentials and\nvirtualization capabilities, executes fast preflight sanity checks, and applies\nruntime overrides before running the pipeline.\n\n## Command Definition\n\n- **Command:** `\u002Fmantis-launch`\n- **Description:** Launches automated multi-agent vulnerability discovery and\n  validation campaigns.\n- **Execution Commands:**\n  ```bash\n  python3 \"${MANTIS_HOME:-\u002Fpath\u002Fto\u002Fmantis}\u002Freference\u002Fscripts\u002Flaunch.py\" \u003Ctarget_file_or_dir> [flags...]\n  \"${MANTIS_HOME:-\u002Fpath\u002Fto\u002Fmantis}\u002Freference\u002Frun.sh\" \u003Ctarget_file_or_dir> [flags...]\n  ```\n\n**Path Anchoring Requirement (CRITICAL)**: The launch scripts reside within the\nMantis installation directory at `reference\u002Fscripts\u002Flaunch.py` and\n`reference\u002Frun.sh`. **You MUST invoke these scripts via an absolute path or via\n`$MANTIS_HOME`**. NEVER execute `.\u002Freference\u002Frun.sh` or\n`python3 reference\u002Fscripts\u002Flaunch.py` using a relative path inside audited\ntarget repositories.\n\n- **CLI Options:**\n  - `target` (positional): Path to a single source file (e.g. `src\u002Fauth.py`) or\n    a root repository directory (e.g. `.` or `\u002Fpath\u002Fto\u002Frepo`).\n  - `--sandbox` \u002F `-s`: Override sandbox mechanism (`static-only`, `gvisor`,\n    `microsandbox`, `gce`).\n  - `--model` \u002F `-m`: Override AI model (e.g. `gemini-3.8-flash`,\n    `vertex_ai\u002Fclaude-opus-5`, `vertex_ai\u002Fzai_org\u002Fglm-5.2-maas`,\n    `openai\u002F{MODEL_ID}`).\n  - `--api-base`: Custom endpoint URL for OpenAI-compatible LLM deployments\n    (e.g. `http:\u002F\u002Flocalhost:8000\u002Fv1`).\n  - `--reasoning-effort`: Reasoning effort level (`low`, `medium`, `high`).\n  - `--timeout`: LLM request timeout in seconds.\n  - `--db` \u002F `-d`: Custom path to SQLite knowledge database (default:\n    `knowledge.db`).\n  - `--scan-mode`: Scan scope strategy (`auto`, `whole`, `file-by-file`,\n    `cross-functional`, `changed`). Use `changed` (without `--resume`) on the\n    same `knowledge.db` to scan newly added\u002Fedited files and verify whether\n    prior findings touching them are `still_present` or `fixed`.\n  - `--resume [RUN_ID]`: Resume an interrupted or partially failed run (latest\n    run for target when `RUN_ID` is omitted), inheriting its recorded scan mode.\n    Cannot be combined with a different `--scan-mode`.\n  - `--workflow` \u002F `-w`: Path to custom `workflow.json` layout definition.\n  - `--preflight-only` \u002F `--test` \u002F `--preflight`: Run preflight checks and exit\n    without starting the campaign.\n  - `--probe` \u002F `--probe-llm`: Actively probe LLM reachability and provider\n    credentials during preflight with a minimal test prompt (`test`, max 256\n    tokens).\n  - `--interactive`: Launch interactive configuration wizard before execution.\n  - `--dry-run`: Display launch plan and indexed files without calling AI\n    models.\n  - `--no-auto-configure`: Disable automatic detection and resolution of default\n    placeholders.\n\n## Automated Auto-Healing & Preflight\n\nBefore starting a security campaign, `mantis-launch`:\n\n1. **Placeholder Auto-Detection**: Inspects `workflow.json` for unconfigured\n   defaults (e.g. `project: \"YOUR_PROJECT_ID\"`).\n2. **Capability Auto-Healing**: If unconfigured, automatically detects host\n   capabilities (GCP project from `gcloud`, `\u002Fdev\u002Fkvm` for microVMs, or `runsc`\n   for gVisor) and auto-updates `workflow.json` or falls back safely to\n   `static-only`.\n3. **Preflight Sanity Check**: Runs a ~1s preflight check verifying that LLM\n   credentials are valid and the selected sandbox environment is operational.\n\n## Common CLI Workflows\n\n### 1. Launch Standard Review on Target File or Repository\n\n```bash\n# Scan a specific file\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" src\u002Fserver\u002Fauth.py\n\n# Scan an entire repository\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" .\n```\n\n### 2. Launch with Static Analysis Only (Zero Sandbox Requirements)\n\n```bash\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --sandbox static-only\n```\n\n### 3. Launch with Specific Model (e.g. Claude or Custom OpenAI Server)\n\n```bash\n# Vertex AI Claude\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --model vertex_ai\u002Fclaude-opus-5\n\n# Local vLLM \u002F Ollama server\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --model openai\u002Fcustom-model --api-base http:\u002F\u002Flocalhost:8000\u002Fv1\n```\n\n### 4. Verify Preflight Readiness Without Scanning\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Flaunch.py\" . --preflight-only\n```\n\n### 5. Incremental Scan & Fix Verification\n\n```bash\n# Resume failed\u002Funstarted campaigns of the baseline run (inherits recorded scan mode)\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --resume\n\n# After fixing code, start a new change-scoped run (do NOT pass --resume)\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --scan-mode changed\n```\n\n### 6. Inspect Results After Launch\n\nAll findings, regression verification checks (`regression_checks`), exploit\nreproduction logs, verified patches, and risk calibration scores are recorded in\n`knowledge.db`. Query guidance using `mantis-advise`:\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fadvise.py\" --file src\u002Fserver\u002Fauth.py\n```\n\n## Input\u002FOutput Contract\n\n- **Reads**:\n  - Target source code files (under target path or repository).\n  - `workflow.json` (declarative graph layout and config).\n- **Writes**:\n  - `knowledge.db` (`findings`, `regression_checks`, `campaign_spend`,\n    `coverage_files`, `campaign_artifacts`, `risk_scores`, `learnings` tables).\n  - `sessions.db` (ADK session state trajectories), beside `knowledge.db` unless\n    `sessions_db_path` \u002F `MANTIS_SESSIONS_DB` says otherwise. It grows with\n    every run and is pruned by nobody; each run ends by stating its size. Only a\n    paused or interrupted run reads its sessions again (`--resume`).\n  - Formatted terminal report and execution logs.\n","# Campaign Launcher (\u002Fmantis-launch)\n\n## System Goal\n\nAutonomous Security Review Pipeline Launcher. Initiates end-to-end vulnerability\ndiscovery, independent verification, exploit viability analysis, crash\nreproduction, automated patch generation, and risk calibration campaigns across\na target file or entire codebase repository.\n\nAutomatically detects unconfigured environment placeholders (such as\n`YOUR_PROJECT_ID` in GCE sandboxes), auto-resolves active credentials and\nvirtualization capabilities, executes fast preflight sanity checks, and applies\nruntime overrides before running the pipeline.\n\n## Command Definition\n\n- **Command:** `\u002Fmantis-launch`\n- **Description:** Launches automated multi-agent vulnerability discovery and\n  validation campaigns.\n- **Execution Commands:**\n  ```bash\n  python3 \"${MANTIS_HOME:-\u002Fpath\u002Fto\u002Fmantis}\u002Freference\u002Fscripts\u002Flaunch.py\" \u003Ctarget_file_or_dir> [flags...]\n  \"${MANTIS_HOME:-\u002Fpath\u002Fto\u002Fmantis}\u002Freference\u002Frun.sh\" \u003Ctarget_file_or_dir> [flags...]\n  ```\n\n**Path Anchoring Requirement (CRITICAL)**: The launch scripts reside within the\nMantis installation directory at `reference\u002Fscripts\u002Flaunch.py` and\n`reference\u002Frun.sh`. **You MUST invoke these scripts via an absolute path or via\n`$MANTIS_HOME`**. NEVER execute `.\u002Freference\u002Frun.sh` or\n`python3 reference\u002Fscripts\u002Flaunch.py` using a relative path inside audited\ntarget repositories.\n\n- **CLI Options:**\n  - `target` (positional): Path to a single source file (e.g. `src\u002Fauth.py`) or\n    a root repository directory (e.g. `.` or `\u002Fpath\u002Fto\u002Frepo`).\n  - `--sandbox` \u002F `-s`: Override sandbox mechanism (`static-only`, `gvisor`,\n    `microsandbox`, `gce`).\n  - `--model` \u002F `-m`: Override AI model (e.g. `gemini-3.8-flash`,\n    `vertex_ai\u002Fclaude-opus-5`, `vertex_ai\u002Fzai_org\u002Fglm-5.2-maas`,\n    `openai\u002F{MODEL_ID}`).\n  - `--api-base`: Custom endpoint URL for OpenAI-compatible LLM deployments\n    (e.g. `http:\u002F\u002Flocalhost:8000\u002Fv1`).\n  - `--reasoning-effort`: Reasoning effort level (`low`, `medium`, `high`).\n  - `--timeout`: LLM request timeout in seconds.\n  - `--db` \u002F `-d`: Custom path to SQLite knowledge database (default:\n    `knowledge.db`).\n  - `--scan-mode`: Scan scope strategy (`auto`, `whole`, `file-by-file`,\n    `cross-functional`, `changed`). Use `changed` (without `--resume`) on the\n    same `knowledge.db` to scan newly added\u002Fedited files and verify whether\n    prior findings touching them are `still_present` or `fixed`.\n  - `--resume [RUN_ID]`: Resume an interrupted or partially failed run (latest\n    run for target when `RUN_ID` is omitted), inheriting its recorded scan mode.\n    Cannot be combined with a different `--scan-mode`.\n  - `--workflow` \u002F `-w`: Path to custom `workflow.json` layout definition.\n  - `--preflight-only` \u002F `--test` \u002F `--preflight`: Run preflight checks and exit\n    without starting the campaign.\n  - `--probe` \u002F `--probe-llm`: Actively probe LLM reachability and provider\n    credentials during preflight with a minimal test prompt (`test`, max 256\n    tokens).\n  - `--interactive`: Launch interactive configuration wizard before execution.\n  - `--dry-run`: Display launch plan and indexed files without calling AI\n    models.\n  - `--no-auto-configure`: Disable automatic detection and resolution of default\n    placeholders.\n\n## Automated Auto-Healing & Preflight\n\nBefore starting a security campaign, `mantis-launch`:\n\n1. **Placeholder Auto-Detection**: Inspects `workflow.json` for unconfigured\n   defaults (e.g. `project: \"YOUR_PROJECT_ID\"`).\n2. **Capability Auto-Healing**: If unconfigured, automatically detects host\n   capabilities (GCP project from `gcloud`, `\u002Fdev\u002Fkvm` for microVMs, or `runsc`\n   for gVisor) and auto-updates `workflow.json` or falls back safely to\n   `static-only`.\n3. **Preflight Sanity Check**: Runs a ~1s preflight check verifying that LLM\n   credentials are valid and the selected sandbox environment is operational.\n\n## Common CLI Workflows\n\n### 1. Launch Standard Review on Target File or Repository\n\n```bash\n# Scan a specific file\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" src\u002Fserver\u002Fauth.py\n\n# Scan an entire repository\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" .\n```\n\n### 2. Launch with Static Analysis Only (Zero Sandbox Requirements)\n\n```bash\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --sandbox static-only\n```\n\n### 3. Launch with Specific Model (e.g. Claude or Custom OpenAI Server)\n\n```bash\n# Vertex AI Claude\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --model vertex_ai\u002Fclaude-opus-5\n\n# Local vLLM \u002F Ollama server\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --model openai\u002Fcustom-model --api-base http:\u002F\u002Flocalhost:8000\u002Fv1\n```\n\n### 4. Verify Preflight Readiness Without Scanning\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Flaunch.py\" . --preflight-only\n```\n\n### 5. Incremental Scan & Fix Verification\n\n```bash\n# Resume failed\u002Funstarted campaigns of the baseline run (inherits recorded scan mode)\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --resume\n\n# After fixing code, start a new change-scoped run (do NOT pass --resume)\n\"$MANTIS_HOME\u002Freference\u002Frun.sh\" . --scan-mode changed\n```\n\n### 6. Inspect Results After Launch\n\nAll findings, regression verification checks (`regression_checks`), exploit\nreproduction logs, verified patches, and risk calibration scores are recorded in\n`knowledge.db`. Query guidance using `mantis-advise`:\n\n```bash\npython3 \"$MANTIS_HOME\u002Freference\u002Fscripts\u002Fadvise.py\" --file src\u002Fserver\u002Fauth.py\n```\n\n## Input\u002FOutput Contract\n\n- **Reads**:\n  - Target source code files (under target path or repository).\n  - `workflow.json` (declarative graph layout and config).\n- **Writes**:\n  - `knowledge.db` (`findings`, `regression_checks`, `campaign_spend`,\n    `coverage_files`, `campaign_artifacts`, `risk_scores`, `learnings` tables).\n  - `sessions.db` (ADK session state trajectories), beside `knowledge.db` unless\n    `sessions_db_path` \u002F `MANTIS_SESSIONS_DB` says otherwise. It grows with\n    every run and is pruned by nobody; each run ends by stating its size. Only a\n    paused or interrupted run reads its sessions again (`--resume`).\n  - Formatted terminal report and execution logs.\n",{"name":5,"description":7},"main","7fa04b64bf1c19134a200a280abca65d7cc7031c","reference\u002Fskills\u002Fmantis-launch",236,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis","https:\u002F\u002Fcloud.google.com\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-13 12:33:29",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add google\u002Fmantis --skill mantis-launch",{"tool":62,"command":63},"bunx","bunx skills add google\u002Fmantis --skill mantis-launch",{"tool":65,"command":66},"pnpm","pnpm dlx skills add google\u002Fmantis --skill mantis-launch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Freference\u002Fskills\u002Fmantis-launch\u002FSKILL.md",true,[],[71,97,124,151,162,177],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":41},"01M6992XJHHV0R5N8E392EHRW3","mantis-threat-model","Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-threat-model\u002FSKILL.md",[],[78,79,80,81,82,83,84,85,86,34,87,88,89,90,91,92,93,94,95,96],"mantis threat model","threat model","model","threat","architecture","code","analyzing","knowledge","kb","surfaces","trust","learnings","knowledge base","as","extracting","reading","jsonl","source","source code",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":108,"publishedAt":41},"01M6992TR1BPA5HVF13QRM7EP0","mantis-summarize","Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching code.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-summarize\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[109,110,111,112,22,113,114,83,115,116,117,81,118,119,120,121,122,27,24,123],"summarize","mantis summarize","writing","directory","security","threat modeling","planning","repository","patching","campaign","map","modeling","scripts","make","when",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":135,"publishedAt":41},"01M6992QB4DVMDR2AGT6BPSE3N","mantis-structural-index","Builds a content-addressed semantic-unit index from source code for structural context. Use when a pinned or live codebase is available and structural cross-reference data would improve research quality. Don't use for findings analysis, patching, or reporting.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-structural-index\u002FSKILL.md",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":133,"taxonomyTypeDesc":134},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[136,137,138,139,83,140,141,142,143,117,144,145,146,37,147,148,149,150,24,123],"mantis structural index","index","structural","research","content","reporting","data","analysis","improve","quality","context","research quality","reference","live","unit",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":41},"01M6992KRP2XYWEMV12P5M4GPE","mantis-review","Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-review\u002FSKILL.md",[],[22,158,83,159,117,37,160,161,27,24,95,96,123],"mantis review","validation","filters","false",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":41},"01M6992GKVGJ2NXEJWYFVCN01Q","mantis-researcher","Audits production source code files based on the strategy in workspace\u002Fplan.json. Use when a review plan exists and you need to perform static analysis and deep-dive reviews of targeted files. Don't use for planning, deduplicating, or writing patches.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-researcher\u002FSKILL.md",[],[169,170,111,22,171,83,115,143,172,173,37,34,174,175,27,24,95,176,96,123],"mantis researcher","researcher","static analysis","plan","strategy","deep","you","static",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":41},"01M6992D5WXENF3TW68GM5WPHC","mantis-reproduce","Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to write and execute a script or payload to verify the crash. Don't use for code auditing or patching.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmantis\u002Fblob\u002Fmain\u002Fskills\u002Fmantis-reproduce\u002FSKILL.md",[],[184,185,113,83,117,186,187,188,37,189,190,191,175,24,123],"mantis reproduce","reproduce","verify","write","execute","crash","payload","script"]