project-context
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection surface via codebase analysis. The skill ingests untrusted content from local project files (code, comments, dependencies) to generate documentation used by the agent for future tasks.
- Ingestion points: SKILL.md (Workflows 1 and 2) processes project files using glob and direct reading.
- Boundary markers: No delimiters or warnings are specified to prevent the agent from following instructions embedded within the analyzed code.
- Capability inventory: File system read/write and project analysis capabilities.
- Sanitization: No sanitization or validation of the ingested codebase content is performed before interpolation into the .codemap.md or ARCHITECTURE.md files.
- SAFE: No malicious obfuscation, hardcoded credentials, or external network operations were detected in the provided skill files.
Audit Metadata