grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains no executable scripts, binaries, or unauthorized network operations. It consists of high-level behavioral instructions and configuration metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided plans or designs to generate documentation such as ADRs and glossaries, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided plans and designs provided during the interview process (SKILL.md).
  • Boundary markers: None explicitly defined to separate user-provided content from system instructions.
  • Capability inventory: The skill instructs the agent to create documentation using tool calls (SKILL.md).
  • Sanitization: No sanitization or filtering of user-provided design content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:09 PM
Security Audit — agent-trust-hub — grill-with-docs