Back to skill

Security audit

小郑女娲

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language tool for researching public information and generating persona-style SKILL.md files, with local persistence that users should review before use.

Install only if you want a Chinese-language workflow that researches public material and writes generated skills into your OpenClaw skills directory. Review each generated SKILL.md before relying on it or making it available to future agent sessions, especially for non-public figures or topics with limited sources.

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
Findings (1)

T01 · Skill Instruction Hijacking

Note
Location
references/skill-template.md:93
Finding

Forced Branded Attribution in Generated Skill Files

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions are very broad (e.g. any request to 'distill a XXX' or analyze from 'XXX's perspective'), which can cause unintended activation on ambiguous user input. In an agent setting, this increases the chance the skill runs when the user did not clearly consent to research, persona emulation, or file-generation side effects, potentially producing misleading outputs or triggering downstream actions unexpectedly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states it will automatically generate and save a SKILL.md under a local skills directory, but it does not present this as a clear user-facing warning or ask for consent before writing. Silent local file creation is a meaningful side effect in an agent environment because it can surprise users, clutter or overwrite workspace state, and create persistence that later affects other agent behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The title and all template sections are written in Chinese, indicating the skill output is expected to be generated in Chinese. Because the file does not offer a language choice or explain a justified region-specific requirement, this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown file presents all instructions exclusively in Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally limited to a Chinese-language context.

Content

No source excerpt is available for this finding.