Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample --json` 会打印本次实际执行了哪些检查项。
Security audit
物业公共能耗分摊核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local, user-directed checker for property energy apportionment tables and I found no hidden network use, persistence, credential handling, or destructive behavior.
Install this only if you are comfortable running a local Node-based checker on property energy apportionment tables. It does not appear to send data out or modify records, but its interface and output are primarily Chinese and it is limited to the listed free checks.
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 跑 `node scripts/run.mjs --sample --json` 会打印本次实际执行了哪些检查项。
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample --json` 会打印本次实际执行了哪些检查项。
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample --json` 会打印本次实际执行了哪些检查项。
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The skill’s user-facing name, summary, and primary descriptions are presented in Chinese, and the example inputs/usage are also Chinese-specific. Although there is an English display name and brief English description, the document does not state that users may choose their preferred language or locale, which can violate a language-choice policy.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file’s natural-language instructions, warnings, and user-facing messages are entirely in Chinese, including required input guidance and output notes. This effectively imposes a specific language on users without opt-in, and the file does not document that the skill is intentionally region- or locale-specific.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The comment says non-JSON input is treated as plain-text material, giving '直接粘贴的合同全文' as an example. That documented intent expands the apparent input scope to full contracts, while the manifest and surrounding help text describe this skill as specifically checking public energy meter/apportion detail tables.
- Content