ClawHub
Back to skill

Security audit

two

Security checks for vulnerabilities and agentic risk

Overview

This is a simple informational skill about the cultural symbolism of the number 2, with only minor trigger wording ambiguity.

Installing this skill should only affect how the agent answers questions about the cultural meaning of the number 2. Users who want tighter activation could ask the publisher to replace the open-ended trigger wording with explicit exclusions for unrelated math or technical questions.

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

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description lists several specific examples but then adds "etc.", which leaves the trigger scope open-ended. In a skill manifest, this can make activation boundaries unclear and increase the chance of unintended invocation for general questions about the number 2.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The phrase "当用户询问相关话题时" / "when users ask related topics" is ambiguous because it does not specify what counts as sufficiently related. This weakens trigger specificity and may cause the skill to be selected for adjacent topics outside its intended cultural-symbolism scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.