rwx
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to interact with therwxCLI. This allows for configuration linting, documentation retrieval, and sandbox execution, which are the primary intended functions of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data by pulling documentation and results from the RWX platform. While this is standard functionality for a CI/CD integration, it represents a potential surface for indirect prompt injection. 1. Ingestion points: Output from
rwx docs pullandrwx resultsin SKILL.md. 2. Boundary markers: Absent; no specific delimiters are defined to isolate the documentation content. 3. Capability inventory: Shell command execution via theBashtool. 4. Sanitization: Absent; the skill does not define validation or filtering for the retrieved documentation.
Audit Metadata