ClawHub
Back to skill

Security audit

eco-law-assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Chinese environmental-law lookup and compliance reference with no hidden network access, credential use, persistence, or destructive behavior found.

Before installing, be aware that this is a Chinese-language legal reference skill for PRC ecological-environment law. It appears read-only and offline, but its compliance precheck output should be verified against official sources and qualified legal counsel before business or regulatory decisions.

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
84% confidence
Finding
The skill invokes a local script and references local data files, but it does not declare any explicit tool scope or permissions boundary. In platforms that rely on manifest-level restrictions, this can allow broader-than-expected file read behavior or make runtime access controls ambiguous, increasing the risk that the skill reads unintended local files if the execution path changes or the script is extended.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
This code file contains natural-language strings such as the module description, usage help, and all query results entirely in 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 here.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
SQP-3 applies to all file types and covers language or locale policy issues expressed in natural language. This JSON contains user-facing descriptive content exclusively in Chinese across titles, descriptions, and commentary, but does not indicate that the language is optional, selectable, or justified as a region-specific constraint.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
SQP-3 applies to all file types and covers language or locale policy violations. This JSON data file contains user-facing natural-language content exclusively in Chinese, but there is no accompanying indication in the file that the language is selectable, optional, or justified as a documented region-specific constraint.

Static analysis

No suspicious patterns detected.