skill-sync
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is configured to execute a repository-local Node.js script located at scripts/skill-sync.js for synchronization, checking, and generating repository metadata.
- [COMMAND_EXECUTION]: User-provided skill names are passed as arguments to the execution command. Potential injection risks are mitigated by explicit instructions requiring the agent to validate these names against the local file system's directory structure before passing them to the script.
- [SAFE]: The skill acts as a data processor for SKILL.md files (ingestion point). While boundary markers are not explicitly defined, the skill instructions mitigate indirect prompt injection by strictly enforcing verbatim content copying and prohibiting the expansion or interpretation of variable-like placeholders such as $ARGUMENTS. The primary capability inventory is limited to local file system operations handled by the designated script.
Audit Metadata