apify-integration-development

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads external datasets and actor outputs from Apify, which contain untrusted outsider-authored web content.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (medium risk: 0.30). The skill involves building integrations that start Apify Actor and Task runs (POST /v2/actors/{actorId}/runs, POST /v2/actor-tasks/{taskId}/runs), which incur real platform compute charges and billing (Compute Units, cost controls like maxTotalChargeUsd). This constitutes a direct financial operation (charges/purchases/paid service execution). However, authentication requires validated API tokens or OAuth2 with PKCE, and the skill relies on the underlying platform/API service's authentication layer (Authorization: Bearer <APIFY_TOKEN>) to enforce access control independently of the agent.