ClawHub
Back to skill

Security audit

Payable Test

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is a bounded planning workflow for paid validation tests and repeatedly blocks external actions until exact human approval.

Install only if you want an agent to draft paid-test plans from existing Offer Briefs. Before allowing any real send, post, purchase, charge, contract, or account change, verify the checkpoint details, authority, data basis, regulated-review status, cost, and rollback path yourself.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Brief` from `offer-engine`, including its buyer, scope, exclusions, price
hypothesis, unit economics, smallest payable version, evidence label, delivery
authority, and stop condition. Run Authorization permits private test design,
analysis, and artifact creation without asking for another approval. Route back
to `offer-engine` or `moneyprinter` when a material input is missing or the route
changed. Run Authorization never permits buyer contact, publication, payment,
account mutation, or another external commitment.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.