ClawHub
Back to skill

Security audit

Honeycomb

Security checks across malware telemetry and agentic risk

Overview

This Honeycomb skill is a disclosed connector wrapper with limited tool access and clear confirmation guidance for write actions.

Install this if you want Codex to manage Honeycomb datasets, boards, and markers through OOMOL. Review any marker creation payload before approval, and only run the one-time oo CLI install or OOMOL account connection steps if you trust OOMOL and intend to use that integration.

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
92% confidence
Finding
The manifest description says to use this skill for "ANY Honeycomb request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to route all Honeycomb-related tasks through this skill without sufficient task-specific scrutiny. In a skill that can both read and write data, such broad invocation language increases the chance of unnecessary tool use and unintended state-changing operations if the agent selects the skill too aggressively.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.