Security audit

代码分析工具免费版

Security checks for vulnerabilities and agentic risk

Overview

This analysis skill is not clearly malicious, but it requests command execution and file-writing authority while making inconsistent claims about offline operation and external APIs.

Review before installing. Use this skill only in a sandboxed agent with explicit approval for every command or file change, and avoid sensitive inputs unless the publisher clarifies whether network/API calls can occur and why write/exec permissions are required.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:5
Finding: Excessive Command Execution and Filesystem Write Permissions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (8)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The documentation states that the tool does not require networking and operates locally, yet elsewhere references API calls and network troubleshooting steps. Contradictory security and data-flow claims can mislead users into exposing sensitive inputs under the assumption that data never leaves the machine, when the skill may in fact rely on remote services or network operations.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill is presented as a local, structured analysis tool, but later expands its scope to file handling, API integration, and system command execution. This capability mismatch is dangerous because users or orchestrators may grant broader permissions than expected, enabling unintended side effects such as data exfiltration, filesystem modification, or shell command abuse under a benign-seeming label.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description says the skill can analyze "任意输入" and should be used whenever data analysis, report generation, statistical insights, or visualization are needed. This scope is very broad and lacks clear trigger boundaries or exclusion examples beyond real-time streaming, increasing the chance of unintended invocation for ordinary analysis-related requests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description states "支持中文交互" as a built-in behavior, and the document later sets the default output language to zh-CN. This imposes a language/locale preference without clearly offering the user a choice or requiring opt-in.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: L255-L257 state that free-version results are output as Markdown and can only be manually saved or copied, implying no automated persistence capability. This conflicts with L349, which says the skill supports reading, parsing, and writing files, suggesting automation beyond the stated free-version limitation.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: Documenting external API integration in a skill whose stated purpose is local structured analysis introduces unnecessary outbound data pathways. Even if not overtly malicious, this broadens the attack surface and increases the chance that sensitive code, data, or reports are transmitted to third-party endpoints without users expecting it.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: System command execution is materially more dangerous than what is needed for a structured analysis skill. In this context, exec capability can turn a read/analyze workflow into one that can execute arbitrary local commands, access secrets, alter files, or stage further compromise if user input or analyzed content is ever incorporated into command invocations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The examples set ANALYZE_OUTPUT_LANG="zh-CN" and "language": "zh-CN", reinforcing a fixed locale expectation. Because the documentation does not pair this with an explicit language-choice workflow, it can conflict with a policy requiring user language opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.