alert-manager
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's Data Sources and Instructions explicitly describe connecting to external SEO tool APIs, Google Search Console, and a web crawler to ingest public web content (competitor sites, brand mentions, SERPs, link databases) that the agent is expected to read and that directly drive alerts and response actions (see "Data Sources" and Playbooks referencing Search Console, link database, and brand mentions).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata