pdd
Warn
Audited by Snyk on Mar 10, 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's required workflow (Parameters: "must support multiple input methods: ... URL") and the Research step plus "Sources: Cite references and links in research documents" mandate ingesting and interpreting external web/URL content as part of its process, exposing the agent to untrusted third-party material that can influence decisions.
Audit Metadata