resilience-review
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a systematic process for resilience reviews, prioritizing risks based on evidence and user impact rather than hypothetical scenarios.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external system components (routes, APIs, forms) which may contain untrusted data. This represents a potential injection surface, though it is the primary intended function of the skill.
- Ingestion points: The skill analyzes files, routes, forms, and API definitions as specified in SKILL.md.
- Boundary markers: Instructions mandate mapping trust boundaries and require explicit evidence to justify any finding.
- Capability inventory: The skill invokes internal tool commands including /read-the-damn-docs, /diagnosing-bugs, /tdd, and /visual-review.
- Sanitization: Verification is achieved through the tool-mediated TDD pipeline and diagnostic loops.
Audit Metadata