researchers-verifier

Warn

Audited by Snyk on May 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md and VERIFICATION_CHECKLIST.md explicitly instruct the agent to "open the source document", "test the URL (does it load?)", "click archive links" and verify quotes/dates from cited URLs, which requires fetching and interpreting arbitrary public third‑party web content (news, blogs, archives, etc.) that can materially change verification decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 15, 2026, 02:29 AM
Issues
1
Security Audit — snyk — researchers-verifier