grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes data from the local repository, creating a surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to "explore the codebase" and specifically read existing documentation including
CONTEXT.md,CONTEXT-MAP.md, and files within thedocs/adr/directory (SKILL.md). - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to treat content from the codebase as untrusted data or to ignore instructions embedded within those files.
- Capability inventory: The agent has the capability to explore the file system, read source code and documentation, and write or update markdown files (
CONTEXT.mdand ADRs). - Sanitization: There are no requirements for sanitizing, filtering, or validating the content extracted from the codebase before it is integrated into the agent's context or used to generate new documentation.
Audit Metadata