ClawHub
Back to skill

Security audit

Delivery Proof

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is designed to stage and document delivery proof while repeatedly requiring exact approval before any external delivery, publication, payment, contract, or account action.

Before installing, understand that this skill may help prepare and retain private delivery evidence, including customer or payment-related proof. Use it only where you have authority to handle that material, keep evidence minimized and redacted, and require fresh exact approval before any external send, post, payment, contract, or account change.

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 23)May include surrounding context.

md
Plan`, private fulfillment preparation, any acquisition `Action receipt`, and
the available delivery or buyer-result context. Run Authorization permits
private deliverable creation, checking, evidence preparation, and correction
without asking for another approval. It never permits buyer-facing delivery,
publication, charging, contracting, or account mutation. If the acquisition or
delivery result has not arrived, record the awaited external result and return
to `moneyprinter`; do not invent it. Read `references/acceptance-and-proof.md`