academic-deep-research

Warn

Audited by Snyk on Feb 16, 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). The skill explicitly instructs the agent to run web_search and web_fetch against open web sources (see Tool Configuration and Example workflows in SKILL.md/README.md, including TechCrunch and "healthcare IT forum discussions"), so it ingests and analyzes untrusted public third‑party/user‑generated content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:28 AM