The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill is highly vulnerable to indirect prompt injection.
Ingestion points: The skill auto-activates when "cron job scheduler" is mentioned, which can be triggered by content within files read by the agent (e.g., via Read or Grep tools).
Boundary markers: There are no boundary markers or explicit instructions to ignore embedded commands within the processed data.
Capability inventory: The skill has access to Bash, Write, and Edit, allowing it to modify system files and execute arbitrary code.
Sanitization: There is no mention of sanitizing or validating inputs before passing them to the execution tools.
[Command Execution] (HIGH): The skill explicitly allows the Bash tool. In the context of "cron job scheduler" tasks, this provides a direct path for the agent to install persistent malicious tasks (e.g., reverse shells) on the host system if the agent is misled by malicious instructions embedded in a project's documentation or codebase.

cron-job-scheduler