gtm-enrichment-deep

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses Sixtyfour AI agents that "browse the web" and "read the company website" (SKILL.md Step 2 and Tips) and also conditionally calls Apollo on public data, meaning the agent ingests and acts on untrusted public web and social content (e.g., company sites, LinkedIn) which can influence fallbacks and outputs.