research-prospect
Warn
Audited by Snyk on Nov 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow runs web research on arbitrary web pages (company basics, recent signals, contacts' public talks and posts) at SKILL.md step 2, which outsiders can publish to but cannot force into the agent's context, so this is low; the Salesforce Account/Opportunity/Contact reads are own-tenant structured data and are not counted.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata