Skills
skills/zeroz-lab/gm-skills/auto-skill-fit/Gen Agent Trust Hub

auto-skill-fit

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution using npx skills find to search for packages and npx skills add to install them.
  • [EXTERNAL_DOWNLOADS]: The skill initiates the download and installation of external agent skills from remote repositories based on the project's detected technology stack.
  • [PROMPT_INJECTION]: The skill ingests data from untrusted project files (such as package.json and requirements.txt) to drive its recommendation engine, which is a form of indirect prompt injection surface. -- Ingestion points: Local project files including package.json, requirements.txt, Cargo.toml, go.mod, and Dockerfile. -- Boundary markers: None; the skill reads and parses these files directly for keyword extraction. -- Capability inventory: Execution of npx commands which can download and run external code. -- Sanitization: Keywords are normalized and filtered by installation count, and all installations require manual user selection and confirmation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 04:10 AM