Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
固定资产处置损益核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local fixed-asset disposal table checker that is clearly scoped and does not show hidden network, credential, persistence, or destructive behavior.
Install only if you are comfortable using a Chinese-language local checker for fixed-asset disposal tables. It processes the file you point it at locally and does not appear to send data out, but it is a free subset and explicitly omits several accounting checks, so users should not treat it as a complete audit or tax review.
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
- 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 (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The natural-language documentation and user-facing messages in this file are written entirely in Chinese, including usage guidance, warnings, and output text. There is no indication that the skill supports language selection or that the Chinese-only constraint is documented as a justified region-specific requirement, which can violate a language/locale choice policy.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The inline comment states that non-JSON input is handled as plain-text material such as a full contract ("例如直接粘贴的合同全文"). That contradicts the surrounding manifest and code intent, which consistently scope the skill to checking fixed-asset disposal tables with headers rather than generic contract documents.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
This is a manifest-type file, so vague-trigger checks apply. The file contains only a generic text payload and does not document any invocation constraints, examples, or negative examples, making the activation scope unclear if this file is used as a skill template or manifest component.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
Natural-language policy checks apply to all file types. The embedded text forces a specific language/locale presentation and does not offer any user choice or document a justified region-specific constraint.
- Content