Security audit
Software Architect
Security checks for vulnerabilities and agentic risk
Overview
This is a plain-text software architecture guidance skill with no executable behavior; the only caveat is that its marketplace capability tags mention OAuth, purchases, and crypto even though the skill text does not use them.
This appears reasonable to install as an architecture-planning skill. Review the visible skill text before use, and do not grant OAuth tokens, payment authority, crypto-wallet access, or other sensitive capabilities based only on the current metadata tags because the skill itself does not explain or need them.
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.