Warn
Audited by Snyk on Aug 8, 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 skill’s required runtime workflow is for an agent to interact with LinkedIn via Linked API cloud browsers to fetch/search profiles and extract structured data, but the provided spec does not describe ingesting outsider-authored free text through an attacker-controlled feed/queue without first selecting specific items (e.g., it’s not an inbox/chat/ticket ingestion path).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata