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
发票作废与红冲核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
The skill runs locally and does not show exfiltration or persistence, but it should be reviewed because it contradicts itself about a tax/declaration check it does not actually perform.
Only install this if you understand it is a local checker for a limited set of ledger arithmetic checks. Do not rely on it for declaration-form revenue difference validation or broader tax compliance unless the publisher fixes the contradictory output and implements or removes that claimed check.
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 (8)
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
- 87% confidence
- Finding
This JavaScript file contains user-facing natural-language strings and documentation entirely in Chinese, including operational guidance and result/disclaimer text, but does not indicate that the skill is China-specific or that the user can choose another language. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The file-level documentation and later result messaging state or strongly imply that a declaration-form revenue difference check is part of the tool’s effective validation, but the implementation does not actually perform that check. In a tax/compliance workflow, this can mislead users into relying on a control that is absent, creating false assurance and causing material discrepancies to go undetected before filing.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 99% confidence
- Finding
The skill explicitly lists the declaration-form inconsistency check under withheld/not-run checks, but the returned disclaimer says that declaration-form difference validation is included. This internal contradiction can cause downstream users, auditors, or calling agents to trust a nonexistent control, which is especially risky in financial/tax reconciliation where omissions affect compliance decisions.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The user-facing display names, summaries, descriptions, trigger phrases, and usage guidance are primarily in Chinese, while the file does not state that the skill is intentionally limited to Chinese-speaking users or offer language selection. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The natural-language description, usage, status messages, and help text are entirely in Chinese, and the file does not indicate any option for users to select another language or locale. Under the policy rule, a skill that effectively enforces a specific language without user opt-in can be a locale-policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The inline documentation states that non-JSON input will be handled as plain-text material such as a 'full contract text', which contradicts the stated capability of checking invoice void/red-flush ledgers. The code does treat arbitrary non-JSON text as input, but the example in the comment points to a different document type and intent than the skill's declared purpose.
- Content