Security audit

Doc Reasoning Analyst Free

Security checks for vulnerabilities and agentic risk

Overview

This document-analysis skill is mostly coherent, but it asks for unrestricted command execution without a clear need or safe scoping.

Review this skill before installing because it grants command execution even though document analysis should normally only need document reading. Use it only in an environment where command execution is restricted or remove `exec` from the allowed tools; do not treat its output as legal advice.

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: Unnecessary Unrestricted Command-Execution Permission
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: L132 的“能力覆盖范围”罗列了大量宽泛关键词，甚至包含“需要数据分析、报表生成、统计洞察、数据可视化时使用”等与本技能文档推理定位不一致的表述。这种触发范围既缺乏明确边界，也与日常常见分析请求重叠，容易让 Agent 在不适用场景下调用该技能。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: L386 明确写明“完全中文化表达，适配中文用户工作流”，文件整体也仅以中文说明交互方式，但未说明是否支持用户按需选择其他语言。这可能构成语言/locale 策略问题，因为技能默认强制特定语言而没有显式用户 opt-in。
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The '已知限制' section says the free edition restricts '结构改进建议', implying that capability is unavailable. However, earlier sections explicitly instruct the agent to provide '结构改进建议' in the standard output and to improve document clarity in the execution protocol, which is a direct contradiction in documented intent.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The limitations section states that '决策准备报告' is locked to the professional version. Yet the manifest description, usage sections, and standard output all describe generating '决策就绪摘要' and preparing users for signing/approval decisions, which materially overlaps with decision-preparation reporting and creates contradictory expectations.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: “长文档分析”“法律相关文档梳理”“商业文档推理强化”等表述较抽象，虽然提供了适用/不适用情况，但仍未给出明确触发短语、边界条件或负例示范，可能造成何时应激活本技能的不确定性。对 markdown 技能说明而言，这属于触发条件不够具体。
Content: No source excerpt is available for this finding.