ClawHub
Back to skill

Security audit

Payable Test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning workflow for paid validation tests, with clear limits that keep external actions staged until exact user approval.

This skill is appropriate to install if you want structured paid-test planning. Before using any generated plan externally, verify the buyer, price, refund terms, data basis, account authority, platform rules, and any regulated-review requirement; do not approve execution when any prerequisite is unknown.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
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.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
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.