ethical-information-ops
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflow (Execution & Monitoring and Detection sections) explicitly instructs monitoring and verification of public social media and web sources—naming tools like TweetDeck, Hootsuite, Botometer, public records databases and SecureDrop—which indicates the agent is expected to ingest and act on untrusted, user-generated third-party content that can influence decisions.
Audit Metadata