eval-readme

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected.
  • [DATA_EXPOSURE]: The skill uses the GitHub CLI (gh api) to retrieve repository metadata and README content. This is standard behavior for its stated purpose and targets public information on whitelisted domains (github.com, raw.githubusercontent.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (README text).
  • Ingestion points: Data enters via gh api calls or raw URL fetches in SKILL.md.
  • Boundary markers: None explicitly defined for the external content.
  • Capability inventory: Limited to reading data and providing analysis; no file-write, subprocess execution, or remote network operations beyond GitHub are present.
  • Sanitization: No specific sanitization of the README content is performed, but the lack of dangerous capabilities mitigates the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 09:28 AM
Security Audit — agent-trust-hub — eval-readme