ClawHub
Back to skill

Security audit

AI Customer Service

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed customer-service workflow skill that uses a local support wiki and routes sensitive or unsupported cases to human support.

Before installing, point SUPPORT_WIKI_PATH or WIKI_PATH at a curated support knowledge base and avoid including raw customer personal data or private internal notes that should not influence customer replies.

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 (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 442)May include surrounding context.

md
- [ ] `SKILL.md` starts with frontmatter and includes `name` and `description`.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction 'Default to Chinese unless the customer uses another language' imposes a language default based on the skill's preference rather than an explicit user choice. This can violate language/locale policy expectations unless the locale constraint is clearly justified or offered as an opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.