grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting data from the codebase and existing documentation to inform its dialogue and updates to documentation files.\n
- Ingestion points: The agent is instructed to "explore the codebase" and read existing context files and ADRs to cross-reference user statements and domain terminology.\n
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the files being read from the project directory.\n
- Capability inventory: The skill has capabilities to read from the codebase and write to specific documentation paths (docs/domain/ and docs/adr/).\n
- Sanitization: There is no mention of sanitizing, validating, or escaping content extracted from the codebase or documentation files before it is processed or used to generate updates.
Audit Metadata