The Agent Skills Directory

[SAFE]: The skill documentation and configuration contain only natural language instructions for structuring a diagnostic conversation with a user.
[SAFE]: No evidence of command execution, network exfiltration, or unauthorized file access was found in the skill workflow or the agent configuration.
[SAFE]: While the skill processes user-supplied narratives, it lacks any high-privilege capabilities (such as shell access or file writing) that could be exploited via indirect prompt injection.

tc-diagnosis