influence-and-negotiation

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (e.g., Phase 2 "Stakeholder deep research", Phase 3 "BATNA market research", references/context-intake.md Step 1, and Phase 4 "Pre-meeting competitive intelligence") explicitly instructs spawning sub-agents to fetch and ingest open/public third‑party sources (LinkedIn, web news, CRM/Slack/APOLLO/OSINT, arbitrary URLs), which the agent must read and use to drive decisions and actions—exposing it to untrusted user-generated/public content that could carry indirect prompt injection.