Back to skill

Security audit

Kimi2.5skill

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow OpenClaw image-runtime troubleshooting skill that may change local model config, but its behavior is disclosed, scoped, and purpose-aligned.

Install only if you are comfortable with a Chinese-language OpenClaw operations playbook that directs an agent to inspect and modify local OpenClaw model configuration. Before applying it, confirm the image-runtime symptom, back up any affected `models.json`, and review the exact provider block being removed.

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
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill body switches into Chinese and presents the operational guidance entirely in that language, with no indication that this is optional or limited to a Chinese-only deployment context. That creates a natural-language locale policy issue because users are not given a language choice or opt-in.

Content

No source excerpt is available for this finding.