research
Warn
Audited by Snyk on Mar 3, 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.md explicitly instructs the agent to "Search for the core concept" and "Read the top results" and to use open/public sources (listed under Information Gathering: news, forums, Wikipedia, blogs) so the agent is expected to ingest and act on untrusted third‑party web content as part of its workflow.
Audit Metadata