behavioral-pm
Warn
Audited by Snyk on May 11, 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). SKILL.md's "Research-First Workflow" explicitly requires the agent to search for a company's leadership principles, recent blog posts, and interview tips from current/former employees — i.e., fetching and ingesting untrusted public web content (user-generated posts and blogs) that the agent must read and use to tailor its answers.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata