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
在建工程转固核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local accounting-table checker with no network, persistence, credential access, or data mutation, though users should not rely on the free version for the date-order checks it lists as not included.
Install only if you want a local Chinese-language ledger checker for the free checks it actually performs. Do not treat it as a complete accounting review: date-order checks, transfer amount exceeding CIP cost, difference-rate thresholds, and post-transfer CIP activity are explicitly not included in this free version.
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
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
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
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The skill metadata promises that each conclusion cites the original text, but the engine only emits generated messages with line numbers and normalized values, not verbatim source excerpts or immutable references. In audit-style workflows this weakens traceability and can mislead users into trusting findings they cannot independently verify against the source input.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This JavaScript file embeds user-facing natural-language descriptions entirely in Chinese, including the prominent file-level notice. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless a locale restriction is explicitly justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The returned advice string is user-facing operational guidance, but it is hardcoded in Chinese and the file provides no mechanism for language selection. This can violate organizational language/locale policy when users are not given a choice or informed of the restriction.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The disclaimer claims the tool checks chronological relationships between start date, transfer date, and depreciation start, but those checks are not implemented. This can cause users to rely on missing controls and accept materially incorrect accounting data, creating a security-relevant integrity issue through false assurance rather than direct code execution.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The JSON template contains only Chinese column headers and content, indicating a fixed language/locale with no opt-in or alternative. This can violate language/locale policy when a skill imposes one language on users without documenting or offering a choice.
- Content