gtm-outbound

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly loads prospect enrichment data from data/gtm/prospects/enriched/ and uses fields like {linkedinPost}, {mutualConnection}, and other public signals (e.g., recent funding, hiringActivity) — i.e., social media/news/user-generated content from third-party sources — and interprets that content as part of message generation, exposing the agent to untrusted third-party input.