The Agent Skills Directory

[SAFE]: The skill follows security best practices for handling sensitive corporate data. It includes a structured deliberation protocol that enforces isolation during critical analysis phases to prevent anchoring and consensus hallucinations.
[DATA_EXPOSURE]: The skill manages highly sensitive business metrics (ARR, MRR, Runway). It addresses this risk through a mandatory 'Anonymization Protocol' that filters sensitive information before any external network activity or API calls.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect injection as it processes multi-sourced data like meeting transcripts. However, it incorporates significant mitigations, including a four-step internal quality loop (Auto-Verification, Peer Validation, Critic Screening, and Founder Feedback) to validate findings before presentation.

c-level-advisor