Security audit
Insurance Knowledge Qa
Security checks for vulnerabilities and agentic risk
Overview
The scanners found no security issues in their reported results and the verdict is benign, though the review is incomplete because Skillspector only partially inspected the single Markdown component.
The verdict is benign with medium confidence, but the evidence is incomplete: Skillspector inspected only part of the Markdown component after a manifest parsing problem and an unresolved local reference. Consider that limitation when deciding whether to install; the scanners did not report specific security issues, but the result is not a guarantee of safety.
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