curate-a-team-library

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes npx ai-agent-skills to perform library initialization, listing, searching, and curation tasks.
  • [EXTERNAL_DOWNLOADS]: The npx utility downloads the ai-agent-skills package from the public registry. The tool also supports importing skills directly from external GitHub repositories.
  • [INDIRECT_PROMPT_INJECTION]: The Discovery Loop ingestion point allows the agent to process metadata and instructions from third-party skills during searching and listing, which could potentially influence agent behavior if the external content is malicious. Ingestion points: discovery loop commands in SKILL.md. Boundary markers: absent. Capability inventory: command execution via npx. Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:32 AM
Security Audit — agent-trust-hub — curate-a-team-library