ClawHub
Back to skill

Security audit

OGT Docs Define

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation guide whose only file-changing examples are explicit, local workflow status markers for definition documents.

Install only if you want this documentation lifecycle convention. When using the shell snippets, run them from the correct definition directory because they modify or remove local status files that represent workflow state.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
79% confidence
Finding
This markdown file includes shell commands that remove files such as `.draft`, `.ready_for_review`, and `.review_requested_at` as part of the workflow. Although the deletions are intentional, the skill text does not include any user-facing warning that these commands modify local files and change workflow state.

Static analysis

No suspicious patterns detected.