grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to explore and analyze the project's codebase, including source files and documentation, to verify claims and update project records. If these files contain malicious instructions, the agent could be influenced to deviate from its intended behavior during the 'grilling' session.
- Ingestion points: The agent reads the root
CONTEXT.md,CONTEXT-MAP.md, Architecture Decision Records (ADRs) indocs/adr/, and source code within thesrc/directory as specified inSKILL.md. - Boundary markers: None present; the instructions do not include delimiters or warnings to ignore instructions found within the analyzed files.
- Capability inventory: The skill requires the agent to have file-read capabilities for codebase exploration and file-write capabilities to update documentation inline.
- Sanitization: No validation or sanitization of the content read from the codebase is specified before it is processed by the agent.
Audit Metadata