uapi-get-github-repo

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to https://uapis.cn to retrieve repository metrics. This domain is not on the trusted organization or well-known service whitelist.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted repository metadata from GitHub.\n
  • Ingestion points: External data such as repository descriptions, owner info, and branch details are retrieved from the API in references/operations/get-github-repo.md.\n
  • Boundary markers: No delimiters or instructions are provided to the agent to ignore or isolate instructions embedded in the retrieved metadata.\n
  • Capability inventory: The skill itself contains no local execution scripts, subprocess calls, or file-writing tools.\n
  • Sanitization: The skill does not implement or describe any validation, escaping, or filtering of the content returned by the API before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:42 AM
Security Audit — agent-trust-hub — uapi-get-github-repo