loom
Warn
Audited by Snyk on May 27, 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 explicitly instructs the agent to "Web-search the topic, find 3-5 high-quality sources" (SKILL.md → Topic query) and requires Raw Capture entries with real URLs/raw_path and creation of Source Briefs and Synthesis Packs (references/schemas.md), so it ingests and reads public third‑party web content that directly drives research, synthesis, and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata