ClawHub
Back to skill

Security audit

Presale One-pass Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Markdown-only workflow guide for controlled implementation and QA, with no hidden code, persistence, credential access, or destructive instructions.

Install this only for projects where you want Codex to execute an already-approved implementation plan end to end. Review the plan and verification matrix first, because the skill can guide normal workspace modifications as part of implementation, but it does not add hidden execution or persistence mechanisms.

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
Content
3. Move to next step only after PASS.

Rules:
- No verification evidence -> no done.
- If preferred test runner is unavailable, use fallback (e.g., unittest) and record it explicitly.
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.