promotion-packet

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s required inputs include “Your evidence” and “Supporters” (e.g., brag-doc content and stakeholder vouching) which are free-form text authored by the operating user’s peers/stakeholders, and that text would be ingested into the agent’s LLM context to generate the promotion packet.