link-reclamation-attribution
Warn
Audited by Snyk on Jul 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow explicitly has the agent “Search web… and crawl data” and “Capture context” (public web pages/mentions discovered at runtime), which can include outsider-authored free text that the agent would ingest into the LLM context for qualification and drafting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata