technology-evaluation

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md "Research Checklist" (Quick/Standard/Deep Research) explicitly instructs reading public README/homepages, GitHub pages, open issues and comparison articles—i.e., ingesting untrusted, user-generated web content—which the agent would use to inform evaluations and could materially influence decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 02:08 PM