grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of configuration metadata and high-level instructions. It contains no scripts, binaries, or command-line execution logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided designs and plans (Ingestion points: SKILL.md). While it lacks explicit boundary markers or sanitization instructions, the skill does not define any capabilities for file writing, network access, or command execution (Capability inventory: None), which prevents the exploitation of processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:55 AM
Security Audit — agent-trust-hub — grill-with-docs