skills-cli
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
bunxandnpxto execute theskillsCLI for package management tasks, which is the intended core functionality of the skill. - [EXTERNAL_DOWNLOADS]: The skill enables downloading and installing skills from external sources like GitHub and GitLab. It mitigates risk by instructing the agent to verify repository reputation (stars, installs) and prioritize well-known publishers (e.g., OpenAI, Microsoft).
- [PROMPT_INJECTION]: The skill processes external search results from the
bunx skills findcommand, creating a surface for indirect prompt injection. Evidence chain: - Ingestion points: Search results from
bunx skills find(SKILL.md) - Boundary markers: Absent
- Capability inventory: Package installation (
bunx skills add), management, and execution (SKILL.md) - Sanitization: Explicit instructions to verify install counts (1K+), source reputation, and repository stars (100+) before recommending or installing a skill.
Audit Metadata