grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted content from the codebase and existing documentation files (e.g., CONTEXT.md, ADRs) to inform its responses, representing a potential surface for indirect prompt injection. Ingestion points: Codebase exploration and documentation files listed in SKILL.md and CONTEXT-FORMAT.md. Boundary markers: None (the skill assumes the repository content is authoritative). Capability inventory: Local file system read and write operations; no network or subprocess execution capabilities were identified. Sanitization: No validation or sanitization is performed on the ingested content before it is used in the prompt context.
  • [SAFE]: No other threat patterns were detected. The skill does not utilize network requests, access sensitive system credentials, or execute arbitrary shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:12 PM
Security Audit — agent-trust-hub — grill-with-docs