account-research
Warn
Audited by Snyk on Feb 28, 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.md explicitly states in "Execution Flow → Step 2: Web Search (Always)" that the agent will run web searches and extract content from public sites (homepage, news, LinkedIn, careers, etc.), which are untrusted third-party sources that the agent reads and uses to drive recommendations and next actions, enabling indirect prompt injection risk.
Audit Metadata