Security audit
Security checks for vulnerabilities and agentic risk
This is a non-executable coaching skill for early-stage founder decision-making, with some broad activation language but no hidden access, persistence, or unsafe automation.
Install this as advice-only founder coaching. Treat its recommendations on firing, fundraising, pivots, and burn as prompts for judgment rather than automatic decisions, and confirm the skill is actually relevant before using it for sensitive company choices.
The activation criteria are broad and subjective, including cues like 'feels comfort-seeking creeping in' and 'cannot tell if they are on the path to success or slow death.' This can cause the skill to trigger outside its intended scope and steer conversations into high-stakes founder advice without clear user intent or role verification.
The 'When to Use' section repeats ambiguous situational triggers such as comfort-seeking, unclear progress, and scaling prematurely, which rely on interpretation rather than objective conditions. In an autonomous agent context, that increases the risk of over-activation and inappropriate advice on sensitive business decisions like hiring, firing, fundraising, or pivoting.
No suspicious patterns detected.
