career-navigator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to perform parallel WebSearch/WebFetch of public sites (e.g., LinkedIn and company pages) and to ingest/synthesize identified people, URLs and market data as part of required workflows (see references/networking-strategy.md's "Use Task tool, WebSearch, and WebFetch" and SKILL.md / Salary Negotiation "Market compensation research via WebSearch"), which exposes it to untrusted, user-generated third‑party content that can materially influence subsequent actions.