ClawHub
Back to skill

Security audit

one

Security checks for vulnerabilities and agentic risk

Overview

This is a simple bilingual informational skill about the cultural meaning of the number 1, with no code execution, data access, or persistence.

Before installing, expect this skill to answer cultural or symbolic questions about the number 1. Its trigger wording may be a bit loose, so it could activate on some broad 'one' queries, but the inspected artifact does not show risky authority, data access, or execution behavior.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The metadata description includes broad English and Chinese example phrases such as 'meaning of number one' and similar natural-language variants, which can match a wide range of ordinary user requests without strict scoping. This is dangerous because ambiguous routing can cause the skill to activate unexpectedly, increasing the chance of irrelevant responses or interference with more appropriate skills, even though the content itself is non-sensitive.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The usage section says to activate when users ask about 'related topics,' but does not define what qualifies as related. This creates an ambiguous activation boundary that may over-trigger the skill for loosely connected queries, reducing routing precision and potentially crowding out other skills better suited to the user's intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.