Back to skill

Security audit

prodecoder

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly transparent and low-privilege, but it explicitly helps analyze and imitate tactics for bypassing platform limits, so users should review it carefully before installing.

Install only if you are comfortable with a Chinese-language social-media analysis tool that may contact submitted URLs through a browser agent. Do not submit private or authenticated links, and do not use the evasion-analysis output to bypass platform moderation, ranking, or rate-limiting rules.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and feature text are presented entirely in Chinese and do not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-language context. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Ssd 2

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises '网安级审计' of how creators use homophones and variant characters to bypass platform rate-limiting/moderation and also promises directly reusable imitation prompts. In context, this goes beyond neutral analysis and facilitates evasion of platform safety controls, making abuse easier to reproduce at scale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This code contains natural-language instructions and descriptions in Chinese only, including the main docstring that explains the skill's behavior. Under the policy rule, forcing a specific language without user opt-in is a locale/language policy concern because users are not offered any language choice or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The main skill logic docstring is written only in Chinese and describes how the skill operates in the OpenClaw environment. Because this is natural-language guidance embedded in the skill and no language choice or region-specific justification is provided, it may violate the language/locale policy.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly says it will call an external browser agent to fetch metadata from a user-supplied URL, but it does not disclose this outbound network action or its privacy implications. That can mislead users into submitting internal, sensitive, or tracking URLs without understanding that the system will contact them.

Content

No source excerpt is available for this finding.