anti-duplication
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze contents from the user's codebase through semantic and literal searches. This creates a vulnerability where malicious instructions embedded in the code being searched (e.g., in comments or string literals) could influence the agent's behavior during the implementation phase.
- Ingestion points: Results from
mgrep,grep, andgloboperations as described in Step 3 of the workflow inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" directives to wrap the search results before analysis.
- Capability inventory: The skill has the capability to write or modify project files based on its analysis of existing patterns (Step 6: Implement with reuse).
- Sanitization: No sanitization or validation mechanisms are mentioned for the codebase content retrieved during the search strategies.
Audit Metadata