career-transitions

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow and SKILL.md explicitly instruct using public, user-generated sources (e.g., "check levels.fyi", "research Glassdoor/Blind", "find people via Twitter/X, dev.to, company blog bylines", and join public Discord/Slack communities) to gather compensation data, contacts, and evidence that the agent/user is expected to read and use to update scorecards and make decisions, which exposes it to untrusted third‑party content.