The Agent Skills Directory

[SAFE]: The skill implements a logical troubleshooting methodology (Incident Triage) using character-based mnemonics. Analysis of the instructions, evaluation cases, and reference files shows no evidence of malicious patterns.
[PROMPT_INJECTION]: No prompt injection or safety bypass patterns were detected. The skill includes instructions to avoid role-playing unless requested and focuses strictly on incident triage objectives.
[REMOTE_CODE_EXECUTION]: There are no commands or instructions that download or execute remote code. The workflow is entirely based on natural language analysis and structured reporting.
[DATA_EXFILTRATION]: No network operations, sensitive file access, or hardcoded credentials were found. The skill operates on user-provided incident data within the agent's context.
[COMMAND_EXECUTION]: The skill does not instruct the agent to execute shell commands, manage processes, or modify the host system.
[EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository for project provenance (github.com/N0zoM1z0/gensokyo-monochrome-heart). This is a legitimate documentation link to the author's other work and does not involve automated downloads or execution.

reimu-incident-triage