grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists primarily of documentation and configuration files. The main instruction in SKILL.md is a high-level directive to invoke other skills ('grilling' and 'domain-modeling').
  • [REMOTE_CODE_EXECUTION]: While UPSTREAM.md mentions installation commands using npx, these are provided as documentation for the user to install the package manually and are not executed by the skill itself during runtime. The commands target the author's own repository (light-cheng).
  • [INDIRECT_PROMPT_INJECTION]: The skill mentions it 'creates docs' based on an interview process. While it processes user input, it does not have the capabilities (file writes or network access) to cause harm, and it lacks the surface for autonomous execution of malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 01:50 PM