ClawHub
Back to skill

Security audit

AI KEY·短命令

Security checks for vulnerabilities and agentic risk

Overview

This is a small alias skill that redirects users to the AI KEY main skill, with some minor clarity and supply-chain cautions but no evidence of hidden or automatic unsafe behavior.

Install this only if you intend to use AI KEY and trust the iamzifei/aikey source. If the main AI KEY skill is missing, review the source before running the suggested global npx install command, because it is not pinned to an immutable version.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest lists triggers including "/钥匙" at L06, but the English trigger list at L09 omits it, and later the document says there is only one alias and warns against adding others at L41-L42. This inconsistency makes activation scope ambiguous and could cause unintended or unclear invocation behavior.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding
The skill instructs users to run `npx skills add iamzifei/aikey -g --all` without pinning a specific package version. That creates a supply-chain risk: future upstream changes, compromise of the package, or dependency hijacking could cause users to install unexpected or malicious code. In this context the risk is real because the command is presented as the canonical recovery path when the target skill is missing.

Natural-Language Policy Violations

Low
Confidence
76% confidence
Finding
The skill metadata and description present both Chinese and English instructions, but there is no statement about respecting the user's preferred language or offering a language choice. For an organizational language/locale policy review, this can be a policy issue if the skill implicitly defaults to mixed-language output without user opt-in.

Static analysis

No suspicious patterns detected.