research-wiki

Warn

Audited by Snyk on May 14, 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 explicitly requires in full mode an "official-source discovery step per corpus" and to "check official source entrypoints" (mentions external examples like Google Docs / GitHub Docs / Notion), which requires fetching and reading public third‑party content that will directly influence evidence-led decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 14, 2026, 04:43 AM
Issues
1