call-prep
Warn
Audited by Snyk on Feb 15, 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 "Research Supplement" explicitly performs web searches (e.g., "Always run (web search): '[Company] news', '[Company] funding'") and fetches attendee LinkedIn profiles, so the agent ingests untrusted public web and social content as part of its workflow, allowing potential indirect prompt injection.
Audit Metadata