repo-quality-system-lifecycle
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for auditing and ingesting various repository artifacts, including plans, specs, and documents which constitute an untrusted data surface.
- Ingestion points: Processes external content such as plans, specs, docs, skills, and schemas to generate repository ecology reviews and quality audits (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or instructions for the agent to ignore potentially malicious content embedded within the audited files.
- Capability inventory: The skill references running native validation commands (e.g.,
pnpm run eval) and interacting with thestewardCLI tool for evidence gathering and repository adoption. - Sanitization: No specific sanitization or filtering procedures are defined for handling external data before it is processed by the agent.
Audit Metadata