[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R3W6EN962K853EC98P6MF":3,"skill-same:01M79R3W6EN962K853EC98P6MF":43},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M79R3W6EN962K853EC98P6MF","hostile-workflow-state-machine-auditor",null,"Reconstruct states, transitions, prerequisites, forbidden transitions, retries, cancellation, rollback, recovery, partial completion, duplicate, stale, deletion, and restoration behavior.","dylmarriner\u002Fscos-memory","dylmarriner","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F298747229?v=4","01M79R084TPMV4KRR4MK4Q17AD","01M79R085GJDMB005265SBFJ4J",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-workflow-state-machine-auditor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hostile-workflow-state-machine-auditor\ndescription: \"Reconstruct states, transitions, prerequisites, forbidden transitions, retries, cancellation, rollback, recovery, partial completion, duplicate, stale, deletion, and restoration behavior.\"\n---\n\n# hostile-workflow-state-machine-auditor\n\n## Purpose\nReconstruct states, transitions, prerequisites, forbidden transitions, retries, cancellation, rollback, recovery, partial completion, duplicate, stale, deletion, and restoration behavior.\n\n## Threat model\nAssume attacker-controlled or externally influenced data can reach every exposed, internal, asynchronous, persisted, operational, and compatibility boundary. Treat cross-tenant and privilege-changing effects as security-sensitive.\n\n## Adversarial mindset\nDo not trust names, comments, tests, intended reachability, or prior clean labels. Prefer valid-input abuse, alternate interfaces, replay, second-order effects, races, stale state, and partial failure.\n\n## Inputs consumed\nAPI verbs, event types, status fields, idempotency keys, migrations, jobs, recovery tools, admin operations.\n\n## Scope\nAll relevant hand-written code plus security-relevant generated, vendored, schema, migration, deployment, and test boundaries. Read applicable repository instructions and preserve unrelated changes.\n\n## Search strategy\nStart with tracked-file inventory and repository references, then use symbol\u002Freference search, route\u002Fhandler discovery, dangerous-sink search, schema\u002Fconfig inspection, and test mapping. Keep exact paths and line ranges.\n\n## Investigation procedure\nEnumerate state graph; attempt syntactically valid out-of-order, repeated, cancelled, stale, and partially failed transitions; inspect persistence and compensations. Record evidence in audit-results\u002Fhostile-workflow-state-machine-auditor.md using skills\u002Fhostile-repository-auditor\u002Freferences\u002Fartifact-template.md. Inspect callers and callees, success and failure, configuration, persistence, retries, and alternate paths before calling a component clean.\n\n## Questions to ask\nWhat valuable state is reachable with valid calls that the product says should be impossible?\n\n## Cross-component checks\nCompare application checks with DB\u002FRLS, adapters, workers, queues, migrations, external responses, caches, and deployment defaults. Follow identity, tenant, state, and attacker data across every boundary.\n\n## Evidence requirements\nCite exact locations, reachable entry point, attacker preconditions, trace, violated invariant, impact, mitigation search, commands\u002Ftests, and confidence. Separate confirmed, high-confidence, plausible, hardening, and non-issue.\n\n## False-positive elimination procedure\nAttempt to disprove reachability; search for centralized and alternate protections; verify the claimed sink and impact; test a bypass variant; downgrade or close when a real mitigation blocks the path.\n\n## Coverage tracking\nList files\u002Fcomponents, entry points, callers\u002Fcallees, workflows, inputs, trust boundaries, invariants, tests, gaps, and exclusions in the artifact. File opening alone is not coverage.\n\n## Escalation conditions\nEscalate to the master auditor for suspected Critical\u002FHigh impact, cross-tenant or privilege escalation, exploitable chains, contradictory controls, or evidence requiring a second specialist.\n\n## Stopping criteria\nStop only after the assigned scope, alternate interfaces, error\u002Fretry\u002Fconcurrency paths, configuration and persistence effects, and tests have been considered, with gaps explicitly recorded.\n\n## Required output artifact\nA persistent audit-results\u002Fhostile-workflow-state-machine-auditor.md artifact containing every field in the shared template, plus findings and commands with results.\n\n## Self-improvement notes\nRecord any search, heuristic, false-positive lesson, invariant, or cross-component pattern that materially improved detection. Generalize it and propose the owning skill update in audit-results\u002Fskill-improvement-log.md.\n\n## Learned heuristic\nFor every stateful endpoint, test caller-chosen identifiers, duplicate completion, replay, and ownership of terminal transitions; maps and idempotency keys must bind the initiating principal and tenant.\n","# hostile-workflow-state-machine-auditor\n\n## Purpose\nReconstruct states, transitions, prerequisites, forbidden transitions, retries, cancellation, rollback, recovery, partial completion, duplicate, stale, deletion, and restoration behavior.\n\n## Threat model\nAssume attacker-controlled or externally influenced data can reach every exposed, internal, asynchronous, persisted, operational, and compatibility boundary. Treat cross-tenant and privilege-changing effects as security-sensitive.\n\n## Adversarial mindset\nDo not trust names, comments, tests, intended reachability, or prior clean labels. Prefer valid-input abuse, alternate interfaces, replay, second-order effects, races, stale state, and partial failure.\n\n## Inputs consumed\nAPI verbs, event types, status fields, idempotency keys, migrations, jobs, recovery tools, admin operations.\n\n## Scope\nAll relevant hand-written code plus security-relevant generated, vendored, schema, migration, deployment, and test boundaries. Read applicable repository instructions and preserve unrelated changes.\n\n## Search strategy\nStart with tracked-file inventory and repository references, then use symbol\u002Freference search, route\u002Fhandler discovery, dangerous-sink search, schema\u002Fconfig inspection, and test mapping. Keep exact paths and line ranges.\n\n## Investigation procedure\nEnumerate state graph; attempt syntactically valid out-of-order, repeated, cancelled, stale, and partially failed transitions; inspect persistence and compensations. Record evidence in audit-results\u002Fhostile-workflow-state-machine-auditor.md using skills\u002Fhostile-repository-auditor\u002Freferences\u002Fartifact-template.md. Inspect callers and callees, success and failure, configuration, persistence, retries, and alternate paths before calling a component clean.\n\n## Questions to ask\nWhat valuable state is reachable with valid calls that the product says should be impossible?\n\n## Cross-component checks\nCompare application checks with DB\u002FRLS, adapters, workers, queues, migrations, external responses, caches, and deployment defaults. Follow identity, tenant, state, and attacker data across every boundary.\n\n## Evidence requirements\nCite exact locations, reachable entry point, attacker preconditions, trace, violated invariant, impact, mitigation search, commands\u002Ftests, and confidence. Separate confirmed, high-confidence, plausible, hardening, and non-issue.\n\n## False-positive elimination procedure\nAttempt to disprove reachability; search for centralized and alternate protections; verify the claimed sink and impact; test a bypass variant; downgrade or close when a real mitigation blocks the path.\n\n## Coverage tracking\nList files\u002Fcomponents, entry points, callers\u002Fcallees, workflows, inputs, trust boundaries, invariants, tests, gaps, and exclusions in the artifact. File opening alone is not coverage.\n\n## Escalation conditions\nEscalate to the master auditor for suspected Critical\u002FHigh impact, cross-tenant or privilege escalation, exploitable chains, contradictory controls, or evidence requiring a second specialist.\n\n## Stopping criteria\nStop only after the assigned scope, alternate interfaces, error\u002Fretry\u002Fconcurrency paths, configuration and persistence effects, and tests have been considered, with gaps explicitly recorded.\n\n## Required output artifact\nA persistent audit-results\u002Fhostile-workflow-state-machine-auditor.md artifact containing every field in the shared template, plus findings and commands with results.\n\n## Self-improvement notes\nRecord any search, heuristic, false-positive lesson, invariant, or cross-component pattern that materially improved detection. Generalize it and propose the owning skill update in audit-results\u002Fskill-improvement-log.md.\n\n## Learned heuristic\nFor every stateful endpoint, test caller-chosen identifiers, duplicate completion, replay, and ownership of terminal transitions; maps and idempotency keys must bind the initiating principal and tenant.\n",{"name":5,"description":7},"main","9fe81e1e4bf688b122dd91909327607a8900ebe0","skills\u002Fhostile-workflow-state-machine-auditor","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory","https:\u002F\u002Fgithub.com\u002Fdylmarriner","2026-11-13 14:34:37",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add dylmarriner\u002Fscos-memory --skill hostile-workflow-state-machine-auditor",{"tool":35,"command":36},"bunx","bunx skills add dylmarriner\u002Fscos-memory --skill hostile-workflow-state-machine-auditor",{"tool":38,"command":39},"pnpm","pnpm dlx skills add dylmarriner\u002Fscos-memory --skill hostile-workflow-state-machine-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-workflow-state-machine-auditor\u002FSKILL.md",true,[],[44,50,57,64,71,78],{"skillNo":45,"name":46,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":47,"categories":48,"keywords":49,"publishedAt":18},"01M79R47F6YN5SSZ6HC9GM1DDX","memory-search","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fmemory-search\u002FSKILL.md",[],[],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":18},"01M79R3SHP0A648T8R0CF5MFB8","hostile-test-gap-auditor","Use tests as a map of assumptions and find missing negative, authorization, tenant, failure, race, retry, state, configuration, boundary, and recovery tests.","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-test-gap-auditor\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M79R3NN0HH5YC0R9MA8AEJH7","hostile-repository-auditor","Run a maximum-paranoia, attacker-input-first repository security and correctness audit with independent specialist passes, evidence artifacts, cross-review, fixes, and coverage reconciliation.","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-repository-auditor\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M79R3JPGG4WWNHASB38R5B0X","hostile-persistence-auditor","Audit schemas, models, migrations, constraints, indexes, cascades, ORM\u002Fraw SQL, transaction boundaries, soft deletion\u002Frestoration, tenancy, auth fields, and historical states.","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-persistence-auditor\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M79R3EW501YVAKJY8DJ9BYVP","hostile-integration-auditor","Audit APIs, webhooks, callbacks, brokers, queues, signatures, replay protection, retries, parsing, trust assumptions, delayed\u002Fduplicate responses, and external failure.","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-integration-auditor\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M79R3BFYSDYWV13XV6NNMBTC","hostile-exploit-chain-auditor","Combine validated weaknesses into realistic end-to-end abuse paths, prioritizing low-impact primitives that cross trust boundaries or amplify privilege\u002Fdata access.","https:\u002F\u002Fgithub.com\u002Fdylmarriner\u002Fscos-memory\u002Fblob\u002Fmain\u002Fskills\u002Fhostile-exploit-chain-auditor\u002FSKILL.md",[],[]]