Security audit
AI SENSE Free Tools
Security checks for vulnerabilities and agentic risk
Overview
This skill provides clearly disclosed access to remote utility tools, with no hidden execution or unrelated access in the package.
Enable only the tools you need and review their descriptions before use. Tool inputs leave your machine, so avoid confidential documents, production signing keys, and sensitive webhook payloads. Keep returned access tokens private and scope agent workflows to your requested task. Scanner coverage was complete for the single-file package; the remote service's implementation and deletion guarantees remain unverified.
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