The Agent Skills Directory

[SAFE]: The skill is composed of natural language instructions and configuration metadata. No malicious scripts, obfuscated content, or unauthorized file access patterns were detected.
[PROMPT_INJECTION]: The skill is designed to analyze potentially untrusted content (code changes, designs) via the $ARGUMENTS placeholder. Although this represents an indirect prompt injection surface, the risk is negligible as the skill contains no executable code and does not request any sensitive tool permissions. The instructions explicitly direct the agent to rely on evidence and authoritative documentation rather than blindly following input commands.

ork-assess