ink-recon
Warn
Audited by Snyk on Jun 17, 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). The workflow’s only runtime “outsider” text ingestion is via the WebSearch step in Step 4 (competitor/keyword lookups), where fetched public web content can be read as free-form text by the agent and injected into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata