apollo

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

• Third-party content exposure detected (high risk: 0.80). The people-enrichment sub-skill explicitly accepts LinkedIn profile URLs and calls the Apollo People Match API, then returns the API response JSON (see people-enrichment/SKILL.md workflow steps 1–5), which means the agent ingests and displays untrusted, user-generated social-profile content from third-party sources.