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
水电抄表与账单核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local utility meter and bill reconciliation checker whose behavior matches its stated purpose and does not show hidden network, persistence, credential, or destructive activity.
Before installing, confirm that Chinese-language output and the rule that blank base fees count as 0 fit your workflow. The skill runs locally and does not appear to send data out, but its conclusions are limited to the listed arithmetic checks and should not be treated as a full utility-rate audit.
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 (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 file’s natural-language interface, contract descriptions, inputs, outputs, and user-facing messages are entirely in Chinese, implying the skill is intended to operate only in that language. There is no visible user choice, opt-in mechanism, or explicit justification that this is a China-specific or Chinese-only tool, which can violate language/locale policy requirements.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file repeatedly states that when materials are insufficient, the tool must not reach conclusions and must not apply default values. However, amount recomputation silently treats a missing base fee as 0, which can produce a definitive mismatch or a false pass from incomplete data. In a billing-validation skill, this is an integrity issue: users may rely on incorrect audit results to dispute or approve utility charges.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', but the rest of the file consistently describes the required input as a utility meter reading and billing reconciliation table with headers. This is an active documentation mismatch that could mislead users about acceptable input for the skill.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The JSON content at L2 contains user-facing tabular text and labels only in Chinese, with no indication that users can select another language or locale. This can violate a language-choice policy when the skill forces a specific language without opt-in or documented justification.
- Content