apify-lead-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill runs Apify actors and then downloads and displays their results (see SKILL.md Step 4 and reference/scripts/run_actor.js which fetches dataset items from https://api.apify.com/v2/datasets/.../items), meaning it ingests public social media/web-scraped, user-generated content and the agent is expected to read and summarize that content as part of its workflow, which could carry indirect prompt-injection risk.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill performs runtime calls to Apify (e.g., https://api.apify.com/v2/acts/... to start actor runs and mcp.apify.com via the mcpc command to fetch actor schemas), which will execute remote actors (remote code) and return schema/content that the skill uses to build prompts/inputs, so these external URLs directly control execution and prompt behavior.