ai-agent-context
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files to generate documentation, creating a surface for indirect prompt injection.
- Ingestion points: Target directory files (Process step 2) and configuration files like .ai-skills.toml, README.md, and CLAUDE.md (Context Loading step 1).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the source files it reads.
- Capability inventory: The skill possesses file read and write capabilities within the working directory.
- Sanitization: There is no evidence of sanitization or filtering of the content extracted from source files before it is interpolated into the documentation templates.
Audit Metadata