skills-radar

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from job postings and user repositories, establishing an indirect prompt injection surface.
  • Ingestion points: WebSearch results for job descriptions and GitHub repository content (READMEs, file contents) via skill-enrichment.md.
  • Boundary markers: Absent; instructions do not specify delimiters for external content.
  • Capability inventory: Reading and writing local markdown files (skills-inventory.md, learning-plan.md), using Glob, and WebSearch.
  • Sanitization: No explicit filtering or escaping instructions for processed data.
  • [EXTERNAL_DOWNLOADS]: Documentation templates reference the author's GitHub repository (github.com/Zal4DW/career-helper) to facilitate user feedback and project tracking. This is a legitimate vendor resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 04:00 PM
Security Audit — agent-trust-hub — skills-radar