ask
Fail
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands (e.g.,
claude -p "{{ARGUMENTS}}",gemini -p "{{ARGUMENTS}}", andomx ask ...) using the{{ARGUMENTS}}placeholder. This pattern is highly susceptible to shell command injection. A malicious user could provide arguments containing shell metacharacters (such as;,|,&&, or backticks) to break out of the intended command and execute arbitrary code on the underlying host system. - [DYNAMIC_EXECUTION]: The skill utilizes dynamic string construction for shell execution. By instructing the agent to wrap user-provided input directly into a command-line string, it creates an insecure runtime execution environment where the boundary between data and code is not maintained.
Recommendations
- AI detected serious security threats
Audit Metadata