collaborating-with-claude
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/claude_bridge.pyscript executes theclaudeCLI viasubprocess.Popen. It implements security best practices by usingshell=Falseand passing arguments as a list, preventing shell injection at the bridge level.\n- [PROMPT_INJECTION]: The skill exposes a prompt injection surface as it passes user-provided text directly to the Claude Code CLI, which has capabilities including shell execution and file modification.\n - Ingestion points: Instructions are accepted through the
--PROMPTparameter inscripts/claude_bridge.py.\n - Boundary markers: The script and its associated prompt templates do not employ explicit boundary markers or delimiters for user-provided data.\n
- Capability inventory: The underlying
claudetool can execute arbitrary shell commands, read/write files, and interact with the environment through MCP tools.\n - Sanitization: No input sanitization or validation is performed on the prompt text before transmission to the CLI.
Audit Metadata