The Agent Skills Directory

[COMMAND_EXECUTION]: The instruction to run taskmd list $ARGUMENTS uses direct shell interpolation of the $ARGUMENTS variable. An attacker or malicious input can include shell metacharacters (such as ;, |, &&, or backticks) to execute arbitrary commands on the underlying system beyond the intended taskmd utility.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data via $ARGUMENTS and passes it directly to a powerful tool (Bash) without any sanitization, escaping, or defensive boundary markers to prevent the agent from executing embedded malicious instructions.

list-tasks