contact-research
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to fetch and then use Common Room contact fields (including activity history, Spark summaries, website pages, and CRM fields) which are outsider-authored data from a third-party system, and those returned text fields would be inserted into the LLM context to generate the profile/output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata