grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes existing documentation (CONTEXT.md, ADRs) and explores the codebase to validate user plans. This creates a surface for indirect prompt injection where malicious instructions embedded in the project files could influence the agent's behavior.
- Ingestion points: Reads files from the local repository, including
CONTEXT.md,CONTEXT-MAP.md, and ADR files (SKILL.md). - Boundary markers: None identified; instructions do not explicitly mandate delimiters or 'ignore' instructions when reading file content.
- Capability inventory: The agent can read files, explore the codebase, and write/update documentation files (SKILL.md).
- Sanitization: No validation or sanitization of the content extracted from the codebase is specified.
- [COMMAND_EXECUTION]: The skill is authorized to explore the codebase to answer questions or verify plan consistency. This is a standard capability for developer-centric tools but allows for broad access to the project's source code and configuration.
Audit Metadata