indeed-research

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and retrieves Indeed job listings and descriptions via the Crawlora API, which ingests public job posting text authored by third-party employers.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime API requests to api.crawlora.net through an included shell helper script, representing an unknown third-party service provider with weak provenance.