career-ops-plugin-apify

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context indirectly via Apify dataset items fetched at runtime from api.apify.com in _apify.mjs (fetchJson/fetchDatasetItems returning items), then transformed (e.g., htmlToText(...) from field_map.description and normalized.title/company/location/url) and forwarded through the pipeline by index.mjs (fetch() returning mapped results).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls the Apify API at runtime (APIFY_API_BASE = 'https://api.apify.com/v2') to start user-specified Apify actors which execute remote code and return dataset items that are then injected into the agent pipeline.