Security audit
product-cognition-intake
Security checks for vulnerabilities and agentic risk
Overview
This skill is a markdown-only product-intake helper that turns user-provided product facts into a structured intro format.
Before installing, note that this skill is intended for product-description intake and may steer the agent to ask structured product questions and produce text for an ai_product_intro field. Use the SKILL.md form for a multi-purpose agent and the system-prompt form only if you want a dedicated intake bot.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.