The Agent Skills Directory

[SAFE]: The skill consists of natural language instructions intended to guide an AI agent in helping users break down business assumptions into actionable tasks. No executable code or suspicious patterns were found.- [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files or exfiltrate data. The skill specifically includes a safety guideline advising users not to use employer data, internal records, or unauthorized materials for their projects.- [PROMPT_INJECTION]: The instructions do not contain markers attempting to override the agent's core safety guidelines or bypass its operational constraints.- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts, install unverified packages, or use dynamic execution patterns. It relies entirely on standard logical reasoning and the agent's built-in tools for search and analysis.

tc-action