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
电费分时计价核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local utility-bill arithmetic checker whose file access and script execution are disclosed and aligned with its stated purpose.
Install this only if you are comfortable using a Chinese-language local checker and running its bundled Node script on billing worksheet text. Treat outputs as arithmetic checks over the fields you provide, not as verification of official tariffs, meter readings, or legal billing correctness.
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 (5)
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
- 88% confidence
- Finding
The user-facing instructions and operational guidance are entirely in Chinese, while the English metadata is limited to a brief description. There is no explicit opt-in, language selection mechanism, or notice that the skill operates only in Chinese, which can violate language/locale choice expectations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file’s user-facing documentation and examples are entirely in Chinese, including the contract description, inputs, advice, and result semantics. There is no indication that users may choose another language or that the Chinese-only behavior is limited to a justified region-specific deployment.
- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The skill repeatedly claims it is fully local and requires no network access, yet it permits the Bash tool, which can invoke arbitrary shell commands and potentially make outbound network requests unless separately sandboxed. This creates a trust-boundary mismatch: users may provide sensitive billing data believing the skill cannot exfiltrate it, while the declared tool permissions do not enforce that guarantee.
- Content