Security audit

易软智联数据交互技能

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent EasySoft reporting purpose, but it asks for reusable business credentials and persistent local storage without enough clear safeguards or scoping.

Review this before installing if the EasySoft account can access sensitive financial or tenant data. Use only a dedicated low-privilege account, confirm where credentials are stored and how they can be deleted or rotated, and avoid entering a real password through ordinary chat unless the host provides a masked secret-entry and verified credential-vault flow.

A.I.G

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

Error

Location: SKILL.md:21
Finding: Unsafe Conversational Collection and Undefined Storage of Reusable Credentials
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 256)May include surrounding context.
md
| `SKILL.md` | 使用说明和引导流程（本文件可公开） |

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list includes very generic business terms such as '报表', '数据查询', '欠费', '应收', '实收', and '月报', which can cause the skill to activate for unrelated conversations that merely mention reporting or financial topics. In this skill’s context, unintended activation is more dangerous because the workflow can prompt users for highly sensitive credentials (property company key, username, and password), increasing the chance of credential collection in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger list includes broad business terms such as ‘报表’, ‘数据查询’, ‘欠费’, ‘应收’, and ‘实收’, which may activate the skill during ordinary conversation that is not intended to query EasySoft. In this skill, accidental activation is more dangerous because the flow can prompt for highly sensitive credentials and initiate queries against an external system.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill asks users for a property-company key, EasySoft username, and password, and states that credentials will be validated and later used for report queries, but it does not clearly warn that these secrets will be transmitted to external EasySoft services. This weakens informed consent and can cause users to disclose sensitive enterprise credentials without understanding the external transmission and associated privacy/security implications.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The skill description and all invocation examples are presented only in Chinese, and the document does not state whether other languages are supported or that the skill is intentionally limited to Chinese-speaking users. Under the policy rule, a skill that effectively enforces a specific language without user opt-in can be a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: All trigger phrases, prompts, report names, and interaction examples are written in Chinese, and the document gives no indication that users may choose another language or that the locale restriction is intentional. This can constitute a language policy issue when a skill implicitly forces one language without opt-in.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The documentation states that the skill package includes SKILL.md as the usage and guidance document, but the provided file is SKILL_PUBLISH.md and serves that role here. This is an active documentation inconsistency about the skill's published artifact structure, which can mislead reviewers or operators about which file defines the skill's behavior and guidance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The manifest text for the skill description and short description is entirely in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the policy for natural-language issues, forcing a specific language without user opt-in can be a locale policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.