apify-market-research
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests and summarizes data from untrusted external sources (e.g., Google Maps, Facebook, Instagram), creating an indirect prompt injection surface where malicious instructions in the scraped data could influence agent behavior.
- Ingestion points: External data enters the agent context via the Apify API results fetched in
reference/scripts/run_actor.js. - Boundary markers: The skill does not implement delimiters or instructions to treat the external data as untrusted or to ignore embedded commands.
- Capability inventory: The skill has the capability to execute shell commands (via
mcpcandnode), write files locally, and make network requests. - Sanitization: Data is formatted for output but not sanitized for potential prompt injection attacks.
- [COMMAND_EXECUTION]: The skill's operation depends on the execution of shell commands for the
mcpcCLI tool and a local Node.js script used to manage actor execution and data output. - [EXTERNAL_DOWNLOADS]: The skill utilizes the
@apify/mcpcCLI tool and fetches actor schemas and dataset items dynamically from the Apify platform during runtime.
Audit Metadata