grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) because it is designed to ingest and process untrusted data from the project codebase to drive its logic.
  • Ingestion points: The skill reads content from CONTEXT.md, CONTEXT-MAP.md, Architectural Decision Records in docs/adr/, and source code in src/ (as specified in SKILL.md).
  • Boundary markers: The instructions do not define boundary markers or provide explicit directions to the agent to ignore instructions that might be embedded within the project files it reads.
  • Capability inventory: The skill has the capability to read files from the file system and write to or update documentation files (CONTEXT.md, docs/adr/*.md).
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from the codebase before the agent uses it to suggest answers or update documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 10:44 AM
Security Audit — agent-trust-hub — grill-with-docs