multi-tool-pipeline
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- COMMAND_EXECUTION (HIGH): The instructions in
SKILL.mddirect the agent to execute a script (multi_tool_pipeline.py) located outside the skill's directory, leading to the execution of unvetted code. - REMOTE_CODE_EXECUTION (HIGH): The
workflow.pyfile uses directory traversal (../../../scripts/multi_tool_pipeline.py) to access and likely execute files outside the intended skill scope. - DATA_EXPOSURE (LOW): The hardcoded path
/home/khitomer/Projects/mcp-code-execution-enhancedreveals the host username and local project structure.
Recommendations
- AI detected serious security threats
Audit Metadata