skf-create-stack-skill

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands including grep, rg, and python3 to perform dependency analysis and import counting across the project codebase. These operations are essential to its primary function of structural code analysis.
  • [EXTERNAL_DOWNLOADS]: Employs npx to download and execute the skill-check utility from the NPM registry. This is a standard practice for utilizing well-known package registries to perform automated validation of generated artifacts.
  • [DATA_EXFILTRATION]: Analyzes project manifests and source code files to extract API signatures and usage patterns. This analysis is performed locally to generate documentation, with no evidence of sensitive data being transmitted to unauthorized external endpoints.
  • [PROMPT_INJECTION]: Contains structured workflow instructions and safety constraints (e.g., 'Zero hallucination') designed to maintain agent focus and consistency. No malicious instructions or safety bypass patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 05:05 PM
Security Audit — agent-trust-hub — skf-create-stack-skill