[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73C227F98CSCFWKD491XGYD":3,"skill-same:01M73C227F98CSCFWKD491XGYD":48},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M73C227F98CSCFWKD491XGYD","hermes-tool-guardrails",null,"Yana AI-native (not hermes-agent-derived — see Provenance correction below) command allowlist + approval-gate pattern for safe tool execution. Block dangerous commands by default, prompt for approval on risky ones, auto-deny in non-interactive subagents. Complements YAMTAM's safe-run.sh at the agent decision level. Distinct from [[hermes-tool-loop-guard]], which detects within-turn tool-call failure loops.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fhermes-tool-guardrails\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: hermes-tool-guardrails\ndescription: Yana AI-native (not hermes-agent-derived — see Provenance correction below) command allowlist + approval-gate pattern for safe tool execution. Block dangerous commands by default, prompt for approval on risky ones, auto-deny in non-interactive subagents. Complements YAMTAM's safe-run.sh at the agent decision level. Distinct from [[hermes-tool-loop-guard]], which detects within-turn tool-call failure loops.\n---\n\n## Provenance correction (2026-06-20)\n\nThis skill was originally tagged `license: MIT` \u002F `source: https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent`\nwhen imported (commit `98f1d51b`). After the real upstream source was vendored\nand read (`vendor\u002Fhermes-agent\u002F_upstream\u002F`), a full grep for this skill's\ncontent (`allowlist`, `auto_approve`, `require_approval`, `always_block`,\n\"Approval needed\") found **zero matches anywhere in the actual hermes-agent\nsource**. The real `agent\u002Ftool_guardrails.py` is loop-detection logic only —\nported verbatim as `core\u002Flib\u002Fhermes_adapted\u002Ftool_guardrails.py` and documented\ncorrectly in [[hermes-tool-loop-guard]]. The attribution on this file was\nfalse provenance, not a real hermes-agent pattern. Source\u002Flicense header\nremoved; content below is Yana AI-native guidance, kept because it doesn't\nduplicate the cited rule files below — not because it came from hermes-agent.\n\n# Hermes Tool Guardrails\n\nDefense-in-depth for shell command execution. Works alongside YAMTAM's hook layer — hooks block at the OS level, this skill enforces at the agent decision level before the call is even made.\n\n**Trigger phrases:** \"command approval\", \"allowlist\", \"safe commands\", \"guardrails\", \"restrict tools\", \"auto-deny subagent\", \"command safety\"\n\n---\n\n## Three Execution Modes\n\n| Mode | Context | Behavior |\n|------|---------|----------|\n| **Interactive** | CLI session with human present | Prompt for approval on risky commands |\n| **Non-interactive subagent** | Spawned worker agent | Auto-deny anything not in allowlist |\n| **Cron\u002Fbatch** | Scheduled, unattended | Allow only explicitly approved patterns |\n\n**Default for subagents: non-interactive (safe).** Never pass `--allow-all` when spawning a worker.\n\n---\n\n## Allowlist Config\n\n```yaml\n# .yana\u002Ftool-guardrails.yaml\napproval:\n  auto_approve:\n    - \"git status\"\n    - \"git diff *\"\n    - \"git log *\"\n    - \"npm test *\"\n    - \"cargo test *\"\n    - \"cat *\"\n    - \"ls *\"\n\n  require_approval:\n    - \"git push *\"\n    - \"npm publish *\"\n    - \"cargo publish *\"\n    - \"gh release *\"\n    - \"kubectl apply *\"\n    - \"terraform apply *\"\n\n  always_block:\n    - \"rm -rf *\"\n    - \"git push --force *\"\n    - \"chmod 777 *\"\n    - \"curl * | bash\"\n    - \"eval *\"\n```\n\n---\n\n## Approval Gate Logic\n\n```python\ndef check_command(cmd: str, interactive: bool) -> bool:\n    if matches_always_block(cmd):\n        print(f\"[BLOCKED] {cmd}\")\n        return False\n\n    if matches_auto_approve(cmd):\n        return True\n\n    if not interactive:\n        # Subagent: deny anything not pre-approved\n        print(f\"[DENIED — non-interactive] {cmd}\")\n        return False\n\n    # Interactive session: ask human\n    print(f\"\\n⚠ Approval needed:\\n  {cmd}\\n\")\n    answer = input(\"Allow? [y\u002FN] \").strip().lower()\n    return answer == 'y'\n```\n\n---\n\n## Subagent Tool Restriction\n\nGive subagents only what they need:\n\n```python\ndelegate_task(\n    goal=\"Run the test suite and report failures\",\n    toolsets=[\"terminal\"],\n    disabled_tools=[\n        \"write_file\",    # cannot modify files\n        \"delegate_task\", # no further delegation\n        \"web_search\"     # no internet\n    ]\n)\n```\n\n**Minimum toolset by role:**\n\n| Role | Needs | Does NOT need |\n|------|-------|--------------|\n| Reviewer | Read, Grep | Write, Bash |\n| Tester | Read, Write, Bash | Web, Delegate |\n| Documenter | Read, Write | Bash, Web |\n\n---\n\n## Dangerous Pattern Detection\n\nBeyond the allowlist — always suspicious:\n\n```python\nDANGEROUS_PATTERNS = [\n    r\"rm\\s+-[rf]{1,2}\\s\",       # destructive delete\n    r\"\\|\\s*(ba)?sh\",             # pipe to shell interpreter\n    r\"eval\\s+['\\\"`$]\",          # eval with dynamic content\n    r\"base64\\s+-d.*\\|\",          # decode and pipe\n    r\"curl.*\\|\\s*(ba)?sh\",       # remote script execution\n    r\"sudo\\s+\",                  # privilege escalation\n    r\"chmod\\s+[0-7]*7[0-7]*\\s+\",# world-writable permission\n]\n```\n\n---\n\n## Mutation Verification\n\nAfter write operations, confirm the change happened:\n\n```bash\nbefore=$(sha256sum src\u002Fauth.ts | cut -d' ' -f1)\n# ... write operation ...\nafter=$(sha256sum src\u002Fauth.ts | cut -d' ' -f1)\n[ \"$before\" != \"$after\" ] && echo \"VERIFIED\" || echo \"WARNING: no change\"\n```\n\n---\n\n## YAMTAM Defense Layers\n\n| Layer | Enforces |\n|-------|---------|\n| `safe-run.sh` (hook) | Hard-blocks dangerous shell patterns |\n| `guard-destructive.sh` (hook) | PreToolUse hook for Bash tool |\n| This skill (agent level) | Decision before tool is called |\n| Subagent toolset restriction | Structural prevention at spawn time |\n\n---\n\n## Anti-Fake-Pass\n\n```\n❌ Config defined but not checked before execution\n❌ Interactive mode in cron job — hangs forever\n❌ Same allowlist for orchestrator and workers — workers need tighter restrictions\n❌ \"Approve everything in dev\" — bad habit that leaks to prod\n❌ Skipping mutation verification on critical writes\n```\n\n## See Also\n- `core\u002Frules\u002F02-terminal-validator.md` — YAMTAM hard-block patterns\n- `core\u002Fscripts\u002Fsafe-run.sh` — shell-level enforcement\n- `core\u002Fhooks\u002Fguard-destructive.sh` — PreToolUse hook\n","## Provenance correction (2026-06-20)\n\nThis skill was originally tagged `license: MIT` \u002F `source: https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent`\nwhen imported (commit `98f1d51b`). After the real upstream source was vendored\nand read (`vendor\u002Fhermes-agent\u002F_upstream\u002F`), a full grep for this skill's\ncontent (`allowlist`, `auto_approve`, `require_approval`, `always_block`,\n\"Approval needed\") found **zero matches anywhere in the actual hermes-agent\nsource**. The real `agent\u002Ftool_guardrails.py` is loop-detection logic only —\nported verbatim as `core\u002Flib\u002Fhermes_adapted\u002Ftool_guardrails.py` and documented\ncorrectly in [[hermes-tool-loop-guard]]. The attribution on this file was\nfalse provenance, not a real hermes-agent pattern. Source\u002Flicense header\nremoved; content below is Yana AI-native guidance, kept because it doesn't\nduplicate the cited rule files below — not because it came from hermes-agent.\n\n# Hermes Tool Guardrails\n\nDefense-in-depth for shell command execution. Works alongside YAMTAM's hook layer — hooks block at the OS level, this skill enforces at the agent decision level before the call is even made.\n\n**Trigger phrases:** \"command approval\", \"allowlist\", \"safe commands\", \"guardrails\", \"restrict tools\", \"auto-deny subagent\", \"command safety\"\n\n---\n\n## Three Execution Modes\n\n| Mode | Context | Behavior |\n|------|---------|----------|\n| **Interactive** | CLI session with human present | Prompt for approval on risky commands |\n| **Non-interactive subagent** | Spawned worker agent | Auto-deny anything not in allowlist |\n| **Cron\u002Fbatch** | Scheduled, unattended | Allow only explicitly approved patterns |\n\n**Default for subagents: non-interactive (safe).** Never pass `--allow-all` when spawning a worker.\n\n---\n\n## Allowlist Config\n\n```yaml\n# .yana\u002Ftool-guardrails.yaml\napproval:\n  auto_approve:\n    - \"git status\"\n    - \"git diff *\"\n    - \"git log *\"\n    - \"npm test *\"\n    - \"cargo test *\"\n    - \"cat *\"\n    - \"ls *\"\n\n  require_approval:\n    - \"git push *\"\n    - \"npm publish *\"\n    - \"cargo publish *\"\n    - \"gh release *\"\n    - \"kubectl apply *\"\n    - \"terraform apply *\"\n\n  always_block:\n    - \"rm -rf *\"\n    - \"git push --force *\"\n    - \"chmod 777 *\"\n    - \"curl * | bash\"\n    - \"eval *\"\n```\n\n---\n\n## Approval Gate Logic\n\n```python\ndef check_command(cmd: str, interactive: bool) -> bool:\n    if matches_always_block(cmd):\n        print(f\"[BLOCKED] {cmd}\")\n        return False\n\n    if matches_auto_approve(cmd):\n        return True\n\n    if not interactive:\n        # Subagent: deny anything not pre-approved\n        print(f\"[DENIED — non-interactive] {cmd}\")\n        return False\n\n    # Interactive session: ask human\n    print(f\"\\n⚠ Approval needed:\\n  {cmd}\\n\")\n    answer = input(\"Allow? [y\u002FN] \").strip().lower()\n    return answer == 'y'\n```\n\n---\n\n## Subagent Tool Restriction\n\nGive subagents only what they need:\n\n```python\ndelegate_task(\n    goal=\"Run the test suite and report failures\",\n    toolsets=[\"terminal\"],\n    disabled_tools=[\n        \"write_file\",    # cannot modify files\n        \"delegate_task\", # no further delegation\n        \"web_search\"     # no internet\n    ]\n)\n```\n\n**Minimum toolset by role:**\n\n| Role | Needs | Does NOT need |\n|------|-------|--------------|\n| Reviewer | Read, Grep | Write, Bash |\n| Tester | Read, Write, Bash | Web, Delegate |\n| Documenter | Read, Write | Bash, Web |\n\n---\n\n## Dangerous Pattern Detection\n\nBeyond the allowlist — always suspicious:\n\n```python\nDANGEROUS_PATTERNS = [\n    r\"rm\\s+-[rf]{1,2}\\s\",       # destructive delete\n    r\"\\|\\s*(ba)?sh\",             # pipe to shell interpreter\n    r\"eval\\s+['\\\"`$]\",          # eval with dynamic content\n    r\"base64\\s+-d.*\\|\",          # decode and pipe\n    r\"curl.*\\|\\s*(ba)?sh\",       # remote script execution\n    r\"sudo\\s+\",                  # privilege escalation\n    r\"chmod\\s+[0-7]*7[0-7]*\\s+\",# world-writable permission\n]\n```\n\n---\n\n## Mutation Verification\n\nAfter write operations, confirm the change happened:\n\n```bash\nbefore=$(sha256sum src\u002Fauth.ts | cut -d' ' -f1)\n# ... write operation ...\nafter=$(sha256sum src\u002Fauth.ts | cut -d' ' -f1)\n[ \"$before\" != \"$after\" ] && echo \"VERIFIED\" || echo \"WARNING: no change\"\n```\n\n---\n\n## YAMTAM Defense Layers\n\n| Layer | Enforces |\n|-------|---------|\n| `safe-run.sh` (hook) | Hard-blocks dangerous shell patterns |\n| `guard-destructive.sh` (hook) | PreToolUse hook for Bash tool |\n| This skill (agent level) | Decision before tool is called |\n| Subagent toolset restriction | Structural prevention at spawn time |\n\n---\n\n## Anti-Fake-Pass\n\n```\n❌ Config defined but not checked before execution\n❌ Interactive mode in cron job — hangs forever\n❌ Same allowlist for orchestrator and workers — workers need tighter restrictions\n❌ \"Approve everything in dev\" — bad habit that leaks to prod\n❌ Skipping mutation verification on critical writes\n```\n\n## See Also\n- `core\u002Frules\u002F02-terminal-validator.md` — YAMTAM hard-block patterns\n- `core\u002Fscripts\u002Fsafe-run.sh` — shell-level enforcement\n- `core\u002Fhooks\u002Fguard-destructive.sh` — PreToolUse hook\n",{"name":5,"description":7},"main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fhermes-tool-guardrails",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill hermes-tool-guardrails",{"tool":40,"command":41},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill hermes-tool-guardrails",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill hermes-tool-guardrails","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fhermes-tool-guardrails\u002FSKILL.md",true,[],[49,57,64,72,80,88],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]