The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected in the instructions or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied goal descriptions to generate task sequences. While this creates a surface for indirect prompt injection, it is a standard part of the skill's planning functionality. The skill provides structured boundary markers (Goal, Current State, Plan Cost) for plan output, which helps maintain context separation.
[NO_CODE]: The skill consists entirely of instructional logic and utilizes pre-defined platform tools; no custom scripts or external code dependencies are included.

goal-plan