ClawHub
Back to skill

Security audit

api-development

Security checks for vulnerabilities and agentic risk

Overview

This API development skill is not clearly malicious, but it gives broad file, command, and network authority without clear limits or confirmation steps.

Install only if you are comfortable giving this skill broad API-development authority. Use it in a sandbox or limited project directory, provide least-privilege API keys, and explicitly review any proposed command execution, file writes, external API calls, or deployment actions before allowing them.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation rule is overly broad, telling the agent to use this skill whenever the user needs anything related to API development. Because the skill exposes read, write, and exec tools and claims deployment/orchestration abilities, a vague trigger increases the chance the agent will invoke a high-impact skill in contexts where safer, narrower handling would be appropriate.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill describes constructing API requests, calling external services, parsing results, and elsewhere advertises file writing, command execution, and deployment, yet it does not clearly require user confirmation before system-impacting actions. In an agent setting, this can lead to unintended outbound requests, local modifications, or command execution based on ambiguous prompts, increasing the risk of data leakage, destructive changes, or abuse of privileged tooling.

Static analysis

No suspicious patterns detected.