verify-readme-features

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for documentation auditing and performs read-only operations on local files.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from README files and source code, presenting an indirect prompt injection surface. 1. Ingestion points: reads README.md and source files. 2. Boundary markers: None. 3. Capability inventory: File reading and searching only. 4. Sanitization: None. These factors are considered low risk given the lack of sensitive capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:42 AM