prospect-research
Warn
Audited by Snyk on May 14, 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 research workflow explicitly requires web searches of public sources (e.g., "Gather via web search MCP (LinkedIn, company website, press)" and "Search for news" in Phases 2–3) and instructs the agent to read and act on LinkedIn posts, job postings, and public filings as signals that drive outreach decisions, which exposes the agent to untrusted, user-generated third-party content that can change behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata