Missing User Warnings
Medium
- Confidence
- 91% confidence
- Finding
- The skill explicitly instructs the agent to run local Python code based on user-supplied natural-language input, yet does not tell the user that local code or subprocess execution will occur. Even though the example embeds the input as a Python string literal rather than shelling it directly, this still expands the trust boundary and can expose the host to risks from unsafe parser/report code, dependency abuse, or unexpected file/system access during execution.
