gong

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow reads sales conversation data and transcripts from Gong via ClawLink, which includes unverified outsider-authored free text from customers and prospects participating in those calls.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs execution of npx @useclawlink/cli, which fetches and runs external code from an unofficial third-party registry without verifiable first-party enterprise provenance, representing an unverifiable runtime external dependency.