ClawHub
Back to skill

Security audit

Airbrake

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Airbrake connector helper that uses the OOMOL oo CLI and does not show hidden, destructive, or deceptive behavior.

Install this only if you intend to use OOMOL’s oo CLI with a connected Airbrake account. Review the Airbrake scopes you grant, and require explicit confirmation before any action marked write or destructive.

SkillSpector

By NVIDIA
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
84% confidence
Finding
The trigger text is extremely broad: it directs use of this skill for any Airbrake-related request, including reading, creating, and updating data. Overbroad routing can cause unintended invocation in contexts where a narrower or safer workflow would be preferable, increasing the chance of unnecessary access to connected account data or accidental state-changing operations.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The instruction to always use this skill instead of calling the API directly removes user or agent discretion without explaining security, audit, or policy constraints. That kind of forced routing can increase blast radius if the skill is selected by default for tasks that do not actually need it, especially because the skill supports both read and write actions against a connected third-party account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.