ClawHub
Back to skill

Security audit

Canny

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Canny connector that uses the OOMOL oo CLI and clearly warns users before write actions.

Install only if you intend to let Codex operate your Canny workspace through OOMOL. Review payloads carefully before approving create or update actions, and be aware that setup may require installing and signing into the oo CLI and connecting Canny with an API key.

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 phrase 'Use this skill for ANY Canny request' is overly broad and can cause the skill to be invoked for vague or incidental Canny mentions, increasing the chance of unintended tool use. In a connector skill that supports write actions, over-triggering raises the risk that an agent routes tasks into a state-changing workflow without sufficient scoping or user confirmation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.