validate-tasks
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
taskmdCLI tool via Bash. The use of the$ARGUMENTSvariable directly in the shell commandtaskmd validate $ARGUMENTSwithout visible sanitization presents a risk for shell command injection. - [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection.
- Ingestion points: Task files processed by the
taskmdtool. - Boundary markers: No delimiters or instructions are used to distinguish between the tool's output and the data within the task files.
- Capability inventory: The skill has access to the
Bashtool. - Sanitization: No sanitization is performed on the input arguments or the file content before processing.
Audit Metadata