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
研发费用辅助账与高新指标核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language ledger checker that reads a user-provided R&D expense table and prints deterministic validation results without network access or persistence.
Install only if you are comfortable using a Chinese-language local checker for R&D auxiliary ledger data. It appears to run locally and not send data out, but users should still avoid pasting unrelated sensitive documents because the tool is designed for ledger tables, not general document review or tax/legal advice.
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
- 93% confidence
- Finding
The natural-language instructions and user-facing descriptions throughout the file are written exclusively in Chinese, including operational guidance and output text. This imposes a specific language/locale on users without any documented opt-in, fallback, or indication that the skill is region-specific only.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The JSON contains a natural-language template entirely in Chinese, with no indication that language selection is optional or that the skill is limited to a Chinese-only regional context. Under the policy, forcing a specific language or locale without user opt-in is a reportable natural-language policy violation.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The manifest lists trigger phrases including “研发费用辅助账对不上,” which is a natural complaint-style phrase a user might say in ordinary conversation rather than an explicit invocation command. Because no negative examples or tighter activation constraints are provided, the trigger scope may be broader than intended and could cause accidental invocation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The comment on loadInput says non-JSON input is treated as plain-text material such as a pasted '合同全文', which suggests broader document intake. However, the surrounding usage/help text and insufficient-input handling consistently require a 研发费用辅助账 with headers, and the engine is invoked only for that ledger-check workflow. This is a documentation-level contradiction about what kind of material the skill is intended to process.
- Content