ClawHub
Back to skill

Security audit

WaiverForever

Security checks for vulnerabilities and agentic risk

Overview

This WaiverForever skill is coherent and disclosed, with read/write actions scoped to the WaiverForever connector and explicit confirmation required for state-changing actions.

Install this only if you want Codex to use your OOMOL-connected WaiverForever account. Review write payloads before approval, since create_template_signing_link and create_waiver_request can change WaiverForever state, and remember that read actions may expose signed waiver data from your account.

SkillSpector

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
97% confidence
Finding
The description says to use this skill for ANY WaiverForever request and instead of calling the API directly, which creates an overly broad routing rule. This can cause an agent to invoke the skill for sensitive read/write operations without enough contextual narrowing or user-confirmation logic, increasing the chance of unintended data access or state-changing actions.

Static analysis

No suspicious patterns detected.