ClawHub
Back to skill

Security audit

Gist

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed GitHub Gist connector that can read, create, update, and delete Gists through OOMOL, with sensitive actions generally called out for confirmation.

Install this only if you want agents to manage GitHub Gists through your OOMOL-connected account. Review payloads before approving creates, updates, stars, forks, comments, or deletes, and treat deletes as potentially irreversible.

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
83% confidence
Finding
The description says to use this skill for "ANY Gist request," which is an overly broad trigger that can cause the agent to invoke the skill in contexts where direct API use, narrower tooling, or additional review would be more appropriate. Because this skill includes write and destructive operations, broad invocation increases the chance of unintended state-changing actions being routed through it.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.