next-task
Fail
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the taskmd CLI while explicitly instructing the agent to pass user-supplied arguments directly into the command line. This allows for command injection if the user provides shell metacharacters such as semicolons, pipes, or backticks.
- [PROMPT_INJECTION]: The skill takes user input and uses it to construct a command without any boundary markers or sanitization, allowing for input that could redirect the agent's behavior or bypass the intended constraints of the command.
Recommendations
- AI detected serious security threats
Audit Metadata