grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill captures user input through an interview process and incorporates it into persistent documentation files, which could lead to indirect prompt injection if malicious content is provided.
  • Ingestion points: User answers to interview questions defined in SKILL.md.
  • Boundary markers: No delimiters or explicit instructions to treat user input as non-executable data are provided.
  • Capability inventory: The skill modifies CONTEXT.md and writes new markdown files to the docs/adr/ directory.
  • Sanitization: No validation or sanitization of user-provided content is performed prior to file-writing operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:21 AM
Security Audit — agent-trust-hub — grill-with-docs