skill-contract-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/check_skill.py) to perform structural validation of a target skill directory. The script uses only the Python standard library and performs read-only operations on theSKILL.mdfile within the target path. - [SAFE]: The skill's primary purpose is validation and structural analysis. It includes built-in safeguards, such as explicitly instructing the agent not to assume the working directory is the skill bundle and requiring absolute paths for file resolution.
- [SAFE]: The Python script implements strict validation logic for filenames and frontmatter syntax (e.g., kebab-case enforcement, length limits, and core field whitelisting), which acts as a defense-in-depth measure against malformed or deceptive skill metadata in the analyzed targets.
Audit Metadata