crawlbase
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage from the official NPM registry. This is a verified tool from the service provider. - [COMMAND_EXECUTION]: The skill relies on running
membraneCLI commands to perform actions and manage web crawling tasks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes HTML content and data from the web via Crawlbase.
- Ingestion points: Data returned from
crawl-urlandget-stored-result(SKILL.md). - Boundary markers: None explicitly defined in the provided instructions.
- Capability inventory: Ability to execute and create actions via
membrane action runandmembrane action create(SKILL.md). - Sanitization: No specific sanitization or filtering of the scraped content is described.
Audit Metadata