crw-self-host
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses multiple package managers (npm, pip, cargo, brew, apt) to download and install components. The resources are hosted on official registries and vendor-controlled infrastructure.
- [REMOTE_CODE_EXECUTION]: Instructions include a shell-piped download (curl | sh) from the vendor's domain (fastcrw.com) for automated installation.
- [COMMAND_EXECUTION]: System-level installation steps for Linux distributions require the use of sudo to modify repository configurations and install packages.
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the web, creating a potential surface for indirect prompt injection. (1) Ingestion points: External URLs processed via scrape and search endpoints. (2) Boundary markers: Handled by the underlying service implementation. (3) Capability inventory: The agent has access to Bash and Read tools. (4) Sanitization: Includes optional sandboxing for document parsing tasks.
Audit Metadata