amazon-jobs-research

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

• Third-party content exposure detected (low risk: 0.10). The workflow searches and reads public job postings from amazon.jobs via the Crawlora API, which constitutes low-risk outsider-authored content because the attacker can publish poison in job descriptions but cannot force delivery without the agent actively searching for it.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes runtime HTTP requests to an arbitrary third-party API service (crawlora.net), representing a common unofficial operational dependency.