The Agent Skills Directory

[SAFE]: The skill contains only natural language instructions and examples for hypothesis generation. It does not include any executable code, scripts, or network operations.
[PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was found. The instructions focus on structured analysis and evidence-based reasoning.
[DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or network requests are present.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or execution.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided business questions and metrics, it lacks any high-privilege capabilities (like file system writes or network access) that could be exploited via indirect injection.

hypothesis-tree