apify
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
membraneCLI to interact with the Apify platform. This includes commands for authentication, connection management, and executing specific Apify actions (e.g., running Actors, fetching datasets). - [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from the global NPM registry. This package is the official tool for the platform provided by the vendor. - [PROMPT_INJECTION]: As the skill is designed to ingest data from Apify (which scrapes external websites), it possesses an indirect prompt injection surface.
- Ingestion points: Data is brought into the agent's context through
membrane action run(e.g.,get-dataset-items) and themembrane requestproxy. - Boundary markers: No explicit XML delimiters or specific 'ignore' instructions are provided to isolate untrusted data from the agent's instructions.
- Capability inventory: The agent has the ability to execute shell commands via the
membraneCLI and perform network operations. - Sanitization: The instructions do not specify any validation or sanitization of the content retrieved from the Apify API before it is processed by the agent.
Audit Metadata