simplicity-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted codebase content, presenting a risk of indirect prompt injection where instructions embedded in the analyzed code could influence the agent's behavior.
- Ingestion points: The agent is instructed to read all user-facing behaviors from the code, project documentation (README, CLAUDE.md, ADRs), and git history during Phase 1 and the Justification Search.
- Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings to the agent to ignore instructions found within the processed codebase files.
- Capability inventory: The skill leverages the agent's ability to read arbitrary files, search using
grep, and analyze repository history viagit log. - Sanitization: No sanitization or validation of the ingested code or documentation is required before the agent processes the content for reasoning.
Audit Metadata