skill-vetter

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Provides command snippets using curl and jq for fetching repository statistics and skill code for manual or automated inspection.
  • [EXTERNAL_DOWNLOADS]: Retrieves information from GitHub APIs and raw content domains. These are well-known services and the downloads are necessary for the skill's vetting function.
  • [PROMPT_INJECTION]: The skill's auditing workflow involves processing untrusted third-party data, which presents an inherent surface for indirect prompt injection.
  • Ingestion points: Fetches content from GitHub repositories via the curl commands defined in SKILL.md.
  • Boundary markers: Relies on the agent's application of the provided 'Vetting Protocol' rather than technical isolation of fetched content.
  • Capability inventory: Utilizes shell commands for network access and JSON parsing.
  • Sanitization: Security vetting is logic-driven based on a checklist of prohibited patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:35 PM
Security Audit — agent-trust-hub — skill-vetter