The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run the taskmd CLI utility. It instructs the agent to construct commands using user-provided data from $ARGUMENTS (e.g., taskmd add "[title]"). This pattern creates a surface for command injection if the agent does not properly escape shell-control characters present in the user's input.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data and uses it to drive agent actions.
Ingestion points: User input provided via $ARGUMENTS is used to define command-line arguments and populate task file content.
Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to treat the input as literal data rather than instructions.
Capability inventory: The skill has access to Bash (shell execution), Read (file system access), and Edit (file modification).
Sanitization: Absent. There are no instructions to validate, filter, or escape the content of $ARGUMENTS before processing.

add-task