Security audit
Agent Spec
Security checks for vulnerabilities and agentic risk
Overview
This skill is a planning template for designing bounded AI agents and does not ask to run code, access private data, or install persistent components.
This appears safe to install as a specification-writing aid. Review generated agent specs carefully if they include real tools, durable memory, outbound actions, spending, or irreversible operations, because those risks belong to the agents being designed rather than this skill itself.
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.