curate-skill-repository
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit and inventory external content, including skill packages, pull requests, and repository history, which introduces a potential surface for indirect prompt injection.
- Ingestion points: Repository inventory including current packages, active proposals, and branch history as defined in references/repository-curation-patterns.md.
- Boundary markers: The instructions lack specific delimiters or warnings to ignore embedded instructions within the third-party skill packages being analyzed.
- Capability inventory: The skill utilizes the agent's native capabilities for file system access and git operations; no custom scripts are included.
- Sanitization: No explicit content validation or sanitization steps are defined for the ingested data.
- [NO_CODE]: The skill consists entirely of markdown documentation and instructional guidelines; no executable scripts, binaries, or configuration files for code environments were detected.
Audit Metadata