Security audit
Ai Agent Security Audit
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain-text AI agent security audit guide with no bundled code, persistence, or hidden execution behavior.
Install this only when you want the agent to perform a security review, and give it a clear target scope. Because the described audit may look at tools, MCP servers, plugins, and credential-leak paths, avoid granting access to production secrets or broad systems unless that is intentionally part of the review.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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
