grill-with-docs

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for documentation management and domain modeling. It assists in maintaining a project's CONTEXT.md and Architecture Decision Records (ADRs) by interviewing the user and checking against the existing codebase. No malicious patterns such as exfiltration, privilege escalation, or persistence were found.
  • [SAFE]: Indirect Prompt Injection Surface: The skill ingests untrusted data from the user and the codebase, which is inherent to its function.
  • Ingestion points: User-provided architectural plans and the project's source code files (SKILL.md, README.md).
  • Boundary markers: None explicitly defined to separate processed data from instructions.
  • Capability inventory: Reading codebase files; writing and updating CONTEXT.md and docs/adr/ files (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of external content is implemented in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 04:29 AM
Security Audit — agent-trust-hub — grill-with-docs