Apify
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill includes mandatory instructions in
SKILL.mdrequiring the agent to send a local notification viacurlimmediately upon invocation. While this is an instruction-override pattern, its purpose is for local workflow observability and does not attempt to bypass safety guidelines or exfiltrate data. - [COMMAND_EXECUTION]: The skill's architecture relies on the agent executing local TypeScript files using the
bunruntime (e.g.,bun run examples/instagram-scraper.ts). This is the intended "Code-First" design to improve token efficiency. - [EXTERNAL_DOWNLOADS]: The skill depends on the
apify-clientlibrary, which is an official and trusted package from Apify. It also interacts with the official Apify API atapi.apify.com. - [DATA_EXFILTRATION]: The skill is designed to ingest data from various web sources (Instagram, LinkedIn, Google Maps, etc.) through the Apify platform. This represents the primary functional purpose of the skill and is documented as such.
Audit Metadata