The Agent Skills Directory

[SAFE]: The skill is entirely descriptive and provides a diagnostic workflow for an AI agent to follow. It does not include any scripts, commands, or executable logic.
[SAFE]: No external network connections, data exfiltration patterns, or hardcoded credentials were detected.
[SAFE]: The instructions do not attempt to bypass safety filters or override agent behavior maliciously.
[SAFE]: Although the skill processes untrusted input from Linear issues and user descriptions, it lacks the dangerous capabilities (network access, file writing, or command execution) necessary to exploit indirect prompt injection.

ai-debug