research

Warn

Audited by Snyk on May 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly instructs workers to fetch and ingest live web content (e.g., vendor docs, blog posts, aggregator pages) and attach source URLs and quoted spans that the lead uses in synthesis, so the agent reads and acts on untrusted third‑party webpages.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 10:31 AM
Issues
1
Security Audit — snyk — research