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
预提费用与待摊费用摊销核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local accounting-table checker with disclosed scope and no evidence of network use, persistence, exfiltration, or destructive behavior.
Install only if you are comfortable running a local Node-based checker on accounting table text. It appears to keep data local, but it is not an audit opinion or accounting judgment tool, and the free version intentionally omits several checks that it lists.
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 (5)
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
- 81% confidence
- Finding
The primary trigger and description fields presented to users are entirely in Chinese, and the document body is also Chinese-centric. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
SQP-3 applies to all file types and includes language/locale policy violations. This file’s user-facing descriptions, warnings, sample text, and guidance are entirely in Chinese, with no indication of optional language choice or justification for a Chinese-only constraint.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as a pasted '合同全文' (full contract text), but the manifest and surrounding help text consistently describe the skill as checking a 预提待摊明细表 with headers. This documentation suggests a materially different accepted input type than the skill's intended purpose, creating intent/documentation divergence even though the code still only passes text to the local engine.
- Content