cs-os
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and examples for managing operating system processes using standard POSIX functions like fork(), exec(), and waitpid(). This is the primary intended functionality of the skill.
- [PROMPT_INJECTION]: The skill is designed to generate code based on user-provided queries, which creates a surface for indirect prompt injection. 1. Ingestion points: User queries provided to the agent. 2. Boundary markers: The skill instructions suggest a prefixing pattern (e.g., 'cs-os:') for inputs. 3. Capability inventory: Generates C/C++ code utilizing system calls for process management, memory allocation, and file system access. 4. Sanitization: The skill mandates the inclusion of error-checking logic (using errno) and adherence to POSIX standards in all generated output.
Audit Metadata