setup
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of arbitrary shell commands by passing a user-supplied
eval_cmdparameter to thesetup_experiment.pyscript. This command is intended to be run during the setup phase to establish a baseline metric for experiments. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of untrusted parameters such as
domain,name,target, andeval_cmddefined inSKILL.md. - Ingestion points: Arguments provided directly to the
/ar:setupcommand or via interactive user prompts. - Boundary markers: The skill does not employ delimiters or specific instructions to ensure that user-provided data is not interpreted as instructions.
- Capability inventory: The backend script
setup_experiment.pycan perform shell executions and interact with the file system. - Sanitization: The instructions do not describe any sanitization, validation, or filtering of the user-provided input fields.
Audit Metadata