ClawHub
Back to skill

Security audit

api-review

Security checks across malware telemetry and agentic risk

Overview

This skill is a documented API review workflow with broad activation terms but no hidden, destructive, or credential-seeking behavior.

Before installing, be aware that the skill may activate on general engineering words like design or documentation. Use it when you want an API review, and review any suggested documentation-generation commands before running them in large or sensitive repositories.

SkillSpector

By NVIDIA
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
Confidence
96% confidence
Finding
The manifest trigger list includes very generic terms such as "api", "design", "consistency", "documentation", and "versioning". These overlap heavily with ordinary engineering conversation and do not define clear activation boundaries, increasing the chance that the skill is invoked in contexts unrelated to API review.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.