ClawHub
Back to skill

Security audit

insurance-claim-compass

Security checks for vulnerabilities and agentic risk

Overview

This offline insurance-claim helper is coherent and low-risk, with a practical caution to verify jurisdiction-specific claim guidance locally.

Use this as an offline checklist and draft generator, not as legal advice. Review any generated letters before sending, verify local reporting deadlines and accident-report requirements, and protect any saved claim letters because they may contain policy numbers and loss details.

A.I.G

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

SkillSpector

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
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The string "Police report or EU 'constat amiable' signed at scene" embeds a region-specific requirement in the default guidance, which may not apply to all users or jurisdictions. Because the skill does not ask the user to choose locale or clarify when EU-specific guidance applies, this can create a language/locale policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.