apify
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and executes the official
@apify/actors-mcp-serverpackage from the NPM registry usingnpx. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted web sources (e.g., social media profiles, search results) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data returned from website scraping and social media Actors (
SKILL.md). - Boundary markers: The instructions recommend parsing results and extracting only needed fields, but do not provide explicit delimiters for the raw scraped data.
- Capability inventory: The skill can execute various Apify Actors for web automation and data retrieval.
- Sanitization: The skill does not implement specific sanitization routines for the content of the scraped data before it enters the agent's context.
Audit Metadata