skill-bundle-curator
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/check.pyfile usessubprocess.runto execute internal validation scripts includingvalidate_skill.py,validate_evals.py, andbundle_report.py. These commands are constructed using a list of arguments and target files within the local repository, which is a standard pattern for automated testing and auditing within a development environment. - [DATA_EXPOSURE]: The skill reads various configuration files such as
agent-bundle.json, hook definitions in.cursor/hooks.json, and frontmatter from other skills and agents in the repository. This is the primary intended function of the tool and does not involve exfiltration to external services.
Audit Metadata