scrapingbee
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage from the NPM registry. This is a vendor-provided tool required for managing connections and performing API requests through the Membrane platform. - [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to scrape external websites via the ScrapingBee API. This introduces a surface where malicious instructions embedded in scraped web content could attempt to influence the agent's logic or subsequent actions.
- Ingestion points: Results from web scraping jobs or proxy requests executed via the
membraneCLI (referenced inSKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety guidelines to help the agent distinguish between scraped data and legitimate instructions.
- Capability inventory: The agent has the ability to execute further API actions, run HTTP requests, and manage project data through the Membrane CLI (referenced in
SKILL.md). - Sanitization: No explicit sanitization, filtering, or validation of the retrieved external content is described in the skill documentation.
Audit Metadata