skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The scripts
skill_lint.pyandsync_catalog.pyutilizesubprocess.run()to perform project maintenance tasks, such as running a catalog synchronization script and converting SVG files to PNG. These operations are performed on local files using controlled paths and well-known tools likersvg-convert, representing standard development automation. - [DYNAMIC_CONTEXT_INJECTION]: The
SKILL.mdfile documents the!command`` syntax used by specific AI platforms (e.g., Claude Code). This is provided as instructional content for developers and does not implement any malicious load-time execution within this skill itself. - [INDIRECT_PROMPT_INJECTION]: The skill processes other skill files (reading YAML frontmatter and markdown). It mitigates potential injection risks by using
yaml.safe_load()to parse external data, ensuring that instructions within processed files are not executed as code.
Audit Metadata