Security audit

人身损害赔偿计算

Security checks for vulnerabilities and agentic risk

Overview

This skill is a China-focused personal injury compensation calculator with local reference data and a calculation script; its file reads, optional report writes, and Chinese output are coherent with that purpose.

Before installing, treat outputs as legal/financial estimates rather than advice. Verify current official statistics for the relevant province or city, review any user-provided overrides, and choose output paths carefully when generating Markdown, JSON, or XLSX reports.

A.I.G

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

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (4)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill instructs the agent to read local reference files and write output files such as Markdown, JSON, and XLSX, but it does not declare an explicit tool scope like permissions or allowed-tools. This creates an authorization gap: a host agent may permit broader file access than intended, increasing the chance of unintended reads/writes or abuse if the skill is invoked in a sensitive workspace.

Natural-Language Policy Violations

Medium

Confidence: 82% confidence
Finding: The title and all instructions are written exclusively in Chinese, and the file does not indicate that the skill is China-specific only or offer any language/locale choice. Under the policy rule, a fixed language or locale can be a violation when imposed without opt-in or explicit justification.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: This file contains mandatory user-facing text entirely in Chinese, including the core disclaimer, and the rest of the CLI messages and rendered report are likewise fixed to Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present in this code file.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This markdown file presents all instructions and formulas exclusively in Chinese, and there is no indication that users may choose another language or that the Chinese-only format is an intentional, documented locale constraint. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.