The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions to help users break down goals into actionable steps. No malicious patterns such as remote code execution, persistence, or privilege escalation were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied task descriptions to generate plans. While this is an ingestion point for untrusted data, the skill does not have access to high-risk tools like raw shell execution, file system modification, or network requests. The lack of dangerous capabilities mitigates the risk of indirect injection.

plan-task