founder-playbook
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions focus on established coaching methodologies (GROW, Solution-Focused) and psychological principles. It does not contain any attempts to override safety filters, extract system prompts, or bypass AI constraints.
- [DATA_EXFILTRATION]: There are no commands or logic designed to access sensitive files (like .ssh or .aws) or exfiltrate data to external servers. All external links provided are to well-known and reputable industry sources like a16z, Y Combinator, and the Solana Foundation.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. No 'curl | bash' or similar patterns are present.
- [COMMAND_EXECUTION]: The skill includes configuration in 'package.json' and 'project.json' for a validation script ('quick_validate.py') located in a relative local path. This is a standard development practice for skill validation and does not pose a security risk.
- [EXTERNAL_DOWNLOADS]: All external references are informational links to startup research, mental health resources, and ecosystem grants. These are documented neutrally and originate from well-known technology and venture capital organizations.
Audit Metadata