apify-trend-analysis

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

• Third-party content exposure detected (high risk: 0.85). The runtime path mcpc ... fetch-actor-details (Step 2) and the subsequent run_actor.js calls fetch outsider-authored Apify Actor README/description and dataset items from third-party actors over the network, which are then printed/serialized into the agent’s LLM-visible context (e.g., “Actor description and README” and “TOP 5 RESULTS” text).

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

• Potentially malicious external URL detected (high risk: 1.00). The skill issues runtime API calls (notably a POST to https://api.apify.com/v2/acts/{actorId}/runs?token=...) which starts Apify actors (i.e., executes remote code) and the script depends on those endpoints to function, so this is a runtime external dependency that executes remote code.