deep-research
Warn
Audited by Snyk on Mar 5, 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 using the "deepresearch tool" to collect evidence and citations (Step 3) and to build an evidence table including "URL or reference" that the agent must read, triage, and use to drive drafting, so it ingests and acts on untrusted public/web-sourced content.
Audit Metadata