ing-skill-generator

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the subprocess module to execute local shell commands (e.g., find, ls, cat) for repository analysis, and the claude CLI for evaluation and optimization tasks.\n- [EXTERNAL_DOWNLOADS]: The evaluation review viewer (viewer.html) includes a script tag that fetches the SheetJS library from cdn.sheetjs.com (a well-known library CDN).\n- [SAFE]: The skill's primary functionality involves reading and processing local documentation files to generate structured knowledge bases, which is consistent with its stated purpose as a developer tool.\n- [SAFE]: The skill implements an evaluation framework with graders and comparators to ensure the quality of generated outputs, reducing the risk of accidental prompt injection from source materials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 09:15 PM