Back to skill

Security audit

个人经验转复用流程助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language workflow helper with a read-only validation script and user-controlled AI-HIVE integration, not a hidden or destructive package.

Install this if you are comfortable using a Chinese-language workflow skill and, when AI-HIVE is used, only authorize uploads, paid actions, or external changes after reviewing scope, price, and output. Do not paste passwords, tokens, cookies, verification codes, or full identity documents into the workflow.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The documented purpose says the skill transforms prior work into reusable process assets, but the detected behavior indicates local artifact validation, integrity/path checks, and secret-pattern scanning that are not disclosed. This mismatch is dangerous because users and policy systems may authorize the skill for one low-risk purpose while it performs broader inspection of local data, increasing the chance of unintended data exposure or overreach.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
79% confidence
Finding

The skill references local files and an offline verification script, which implies file-read capability, but it does not declare any explicit tool scope or allowed-tools boundary. Missing capability declarations weakens least-privilege controls and can cause the runtime or reviewer to underestimate what the skill may access.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description and main skill content are written entirely in Chinese and do not state that the skill supports other languages or lets the user choose a preferred language. Under the language/locale policy, a skill should not impose a specific language unless it is clearly justified as region-specific or explicitly opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The note field is written entirely in Chinese and provides mandatory user guidance, but the file does not offer any language selection or opt-in. This can violate language/locale policy when users are expected to interact in a different language or when multilingual support is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
79% confidence
Finding

The entire skill file is written in Chinese and does not state that language selection is optional or limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.