ClawHub
Back to skill

Security audit

Honeybadger

Security checks across malware telemetry and agentic risk

Overview

This skill is not malware, but it needs review because it can submit Honeybadger data while parts of the instructions describe it as read-only and safe to run directly.

Install only if you intend to use OOMOL to submit Honeybadger check-ins, deployments, events, and exception reports. Treat every listed report_* action as a write, inspect the live schema first, and require explicit user confirmation of the exact payload before running it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Confidence
99% confidence
Finding
The manifest describes the skill as suitable for 'searching and reading data,' but every documented Honeybadger action is a report/submit operation that writes data. This mismatch can cause an agent or user to invoke the skill under the false assumption that it is read-only, leading to unintended state changes or telemetry injection into Honeybadger.

Intent-Code Divergence

High
Confidence
98% confidence
Finding
The Safety section says untagged actions are reads, but the listed untagged actions are all 'report_*' operations that submit data to Honeybadger. This incorrect safety model actively misclassifies write actions as safe, increasing the chance an agent executes them without confirmation.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The instruction to use this skill for 'ANY Honeybadger request' is overly broad and can cause automatic routing of unrelated or higher-risk Honeybadger tasks to this skill without validating whether the action is appropriate. In context, this is more dangerous because the skill is mislabeled as read/search-oriented while actually exposing write/report capabilities.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.