Post-Meeting Follow-Up Pack Builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires a "Web Search" in Layer 2 ("run a quick web search for the company" and lists "Required Capabilities: Web Search") and instructs the agent to ingest and weave that public web/company news and competitive intelligence into emails, Slack updates, and confidence assessments, meaning untrusted third-party content from the open web will be read and can materially influence actions.