Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
长期股权投资权益法核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese-language accounting table checker whose disclosed behavior matches the shipped code.
Install only if you want a Chinese-language local checker for equity-method investment tables. You still need to decide the underlying accounting treatment yourself, and any sensitive financial table you provide will be read from the local input file by the Node script, though no network transfer or persistence was found in the inspected artifact.
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 (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Vague Triggers
Medium
- Confidence
- 93% confidence
- Finding
- The manifest text says the trigger phrases include “权益法核算表对不上”, which is a natural, complaint-style phrase a user might say in ordinary conversation rather than a narrowly scoped command. The file does not provide exclusion conditions or clearer trigger boundaries, so this could cause unintended invocation in broader accounting discussions.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The file’s natural-language documentation and user-facing advice/messages are written entirely in Chinese, including operational guidance and output text. There is no indication that the skill is region-specific or that users can opt into a different language, which can violate language/locale policy requirements.
Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- The file’s user-facing description, help text, errors, and output strings are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 95% confidence
- Finding
- The inline documentation states that non-JSON input will be treated as '直接粘贴的合同全文', i.e. contract full text. That contradicts the rest of the file, which consistently documents and enforces that the skill operates on equity-method reconciliation tables with headers, not arbitrary contract text.
Natural-Language Policy Violations
Low
- Confidence
- 90% confidence
- Finding
- The JSON contains only Chinese-language table content, which indicates a fixed language/locale with no user opt-in, alternative language option, or documented regional justification. Under the policy rule for natural-language violations, fixed locale content can be a concern when the skill does not offer choice or explain the restriction.
Static analysis
No suspicious patterns detected.