ask
Fail
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's routing logic uses the pattern
omc ask {{ARGUMENTS}}to execute shell commands. This direct interpolation of user-provided content into a shell command string without quoting or sanitization allows for arbitrary command injection if the input contains shell metacharacters like;,&&,|, or backticks. - [REMOTE_CODE_EXECUTION]: Through the command injection vulnerability in the
omc askexecution path, an attacker or malicious indirect prompt could execute arbitrary scripts or binaries on the host system.
Recommendations
- AI detected serious security threats
Audit Metadata