Back to skill

Security audit

Bigyou

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language decision-comparison skill with a local helper script, and I found no hidden data access, persistence, network retrieval, or destructive behavior.

Install this if you want a Chinese-language option-comparison framework. Expect possible over-activation on broad comparison phrases and note that the bundled analyzer currently crashes for some scene types, so it should be fixed before relying on the script for all examples.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/analyze.py:31
Finding

Input-Triggered Denial of Service Due to Inconsistent Configuration Tuple Shapes

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 (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing instructions, examples, and branding in the README are presented only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only audience. Under the policy, a language or locale constraint should either be optional for the user or clearly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation examples are very broad, including generic phrases like '哪个好' and '怎么选', which can match ordinary conversation and cause the skill to activate outside the user's intent. Over-broad triggering is dangerous because it can intercept unrelated requests, distort routing to more appropriate skills, and increase the chance that users receive decision-framework output when they expected direct factual help.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill metadata and content are written to operate in Chinese without indicating language negotiation or a justified locale restriction. This can lead to poor user comprehension, accidental activation for users in other languages, or incorrect outputs when the surrounding system expects multilingual behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation scope is broad enough to match common, everyday phrases like '哪个好' or '怎么选', which can cause the skill to trigger outside its intended context. Over-broad activation increases the chance of unintended routing, where unrelated user requests are handled by this skill and receive an inappropriate decision-framework response.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file-level description and CLI usage are written only in Chinese, and the skill's logic is built around Chinese scene keywords and output text. There is no indication that users may choose another language or that the Chinese-only constraint is an explicitly documented regional requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description text is entirely in Chinese ("比优 — 选项比较与决策工具") with no indication that the skill supports other languages or that Chinese is required for a region-specific purpose. This can violate language/locale policy if users are not given an explicit language choice or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown template is entirely written in Chinese and does not indicate that language selection is optional or limited to a China-specific audience. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents all user-facing instructions and examples exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.