negotiate

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

• Third-party content exposure detected (high risk: 1.00). The skill's Step 2 explicitly instructs the agent to perform quick salary research on public, user-generated sites (e.g., Levels.fyi and Glassdoor), which the agent would ingest and use to determine market ranges and counter-offer recommendations, creating a path for untrusted third-party content to influence behavior.