webapp-testing
Warn
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The helper script
scripts/with_server.pyusessubprocess.Popenwith theshell=Trueparameter to execute commands provided via the--serverargument. This design allows for the execution of arbitrary shell commands on the host system. - [PROMPT_INJECTION]: The
SKILL.mdfile contains an explicit instruction directing the agent to avoid reading the script's source code before execution ("DO NOT read the source until you try running the script first"). This behavior, while potentially intended to save context tokens, functions as a concealment technique that prevents the agent from verifying the safety of the code it is instructed to run.
Audit Metadata