retro
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes 'build-report.md', 'audit-report.md', and 'state.json', creating an indirect prompt injection surface where malicious content in these reports could manipulate the agent. Ingestion points: SKILL.md (build-report.md, audit-report.md, state.json). Boundary markers: None identified. Capability inventory: Execution of 'legacy/scripts/dispatch/aggregator.sh' and filesystem writes to '.evolve/instincts/lessons/'. Sanitization: Not specified.
Audit Metadata