Security audit
Demo Skill
Security checks for vulnerabilities and agentic risk
Overview
This skill is a simple product-idea critique template with clear limits and no executable or hidden behavior.
This appears safe to install for concise product-idea critiques. Users should still provide only the idea they want reviewed, since the manifest includes file Read capability even though the skill instructs the agent not to read private files.
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.