discover-repository-state
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The instructions focus on structured repository documentation and evidence gathering. No malicious code, prompt injection, or data exfiltration techniques were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading external repository files and documentation, which constitutes an ingestion surface for untrusted data. Risk is mitigated by explicit instructions to separate 'Repository Facts' from 'Documentation' and 'Inference'. 1. Ingestion points: docs/workflow/REPOSITORY_STATE.md, project guides, and arbitrary repository files. 2. Boundary markers: The process strictly separates sections for facts, decisions, planned work, and documentation. 3. Capability inventory: The skill uses file inspection, git status/tooling checks, and artifact committing. 4. Sanitization: No specific sanitization logic is provided, relying instead on the structural separation of concerns.
Audit Metadata