ClawHub
Back to skill

Security audit

Claude API Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Claude API helper with no executable code, persistence, or hidden high-impact behavior.

Installers should understand that this skill is meant for Claude/Anthropic API work, not general LLM app design. The only notable issue is minor trigger ambiguity in the manifest wording; there is no evidence of hidden execution, credential handling, persistence, or destructive 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest’s default prompt begins with "Help me implement this feature," which overlaps with common everyday requests and does not clearly constrain when this skill should activate. Although it later mentions the Claude API, the opening phrasing is broad enough to create ambiguity about trigger scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.