clawhub
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
clawhubCLI tool from the public npm registry and subsequently downloads skill packages from the vendor's registry atclawhub.com. - [COMMAND_EXECUTION]: The skill uses subprocess calls to execute
clawhubCLI commands for logging in, searching, installing, and publishing skills. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the download and integration of third-party instructions (skills) which could potentially contain malicious prompts.
- Ingestion points: External skills are ingested via
clawhub installandclawhub updatecommands referenced inSKILL.md. - Boundary markers: No specific boundary markers or 'ignore' instructions are defined for the content downloaded from the registry.
- Capability inventory: The tool possesses the ability to execute shell commands, manage local file directories (
./skills), and perform network operations via the CLI. - Sanitization: The instructions do not describe automated validation or sanitization of the logic contained within downloaded skills.
Audit Metadata