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 mandatory workflow requires spawning parallel sub-agents and running "deep research" that ingests open/public third-party content (LinkedIn, Glassdoor, web news, Gmail/Outlook, Slack, public forums, etc.) as part of Phase 2/3 preparation and context intake (see references/context-intake.md Step 1 "External sources — use connectors", "Stakeholder deep research" in Phase 2, and "BATNA market research" in Phase 3 of SKILL.md), so untrusted user-generated content is fetched, read, and used to drive tool decisions and next actions.