ClawHub
Back to skill

Security audit

Okta

Security checks across malware telemetry and agentic risk

Overview

This Okta skill is mostly coherent, but it can perform high-impact identity actions and one lifecycle action is not properly guarded by its own safety rules.

Install only if you trust OOMOL and intend agents to administer Okta through it. Require explicit user approval for any user, group, credential, or lifecycle change, including lifecycle_user, even though that action is not tagged as write or destructive in the skill.

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
94% confidence
Finding
The skill instructs the agent to use it for ANY Okta request instead of calling the API directly, creating an overly broad trigger scope. This can cause the skill to intercept unrelated or higher-risk Okta tasks by default, including sensitive write or destructive operations, increasing the chance of unintended actions or unsafe delegation without narrower routing conditions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.