glossary
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted codebase data to generate a CONTEXT.md file that guides future agent behavior.\n
- Ingestion points: Reads codebase naming patterns (types, modules, variable names) and existing CONTEXT.md file as specified in SKILL.md.\n
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when reading code or the glossary.\n
- Capability inventory: File system write access to create and update the CONTEXT.md file at the project root as specified in SKILL.md.\n
- Sanitization: There are no instructions for sanitizing or filtering external content identified during codebase exploration before it is written to the glossary.
Audit Metadata