fact-check-workflow

Warn

Audited by Snyk on May 10, 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 explicitly requires researching and gathering evidence from public third‑party sources (Step 2 "Research the claim" — primary/secondary sources), including social media and web pages, and directs archiving/downloading/reading web pages (Step 3 "Evidence gathering" and "Archiving evidence" mentioning Wayback Machine/Archive.today), so the agent would ingest untrusted public content that can influence ratings and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 10, 2026, 01:39 AM
Issues
1