204-feature-validation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files to generate validation reports, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill reads several artifacts including
overview.md,specs.feature,implementation.md, anddomain-knowledge.md(Step 1, Step 2), and it uses the@exploretool to read production files from the codebase (Step 3).\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the design or code files.\n
- Capability inventory: The skill's capabilities are focused on file reading and codebase analysis. No file-writing, network-exfiltration, or command-execution capabilities were identified that could be easily abused by an injection.\n
- Sanitization: No sanitization, validation, or content filtering is specified for the data ingested from the external files.
Audit Metadata