apify

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the skill can fetch and ingest Apify Actor/task results and logs (e.g., via apify_run_actor_sync, apify_actor_task_run_sync_get, apify_get_dataset_items, apify_get_log), which are outsider-authored free text from third-party Apify actors/datasets into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx @useclawlink/cli", which fetches and executes remote code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli / registry.npmjs.org) at runtime, so the agent depends on externally-run code to function.