ClawHub
Back to skill

Security audit

OpenSpec

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OpenSpec workflow helper that edits project planning/spec files and does not show hidden, destructive, credential, network, or persistence behavior.

Install this if you want agents to use OpenSpec for non-trivial project changes. Be aware it may create or update files under openspec/ and can archive completed changes, so review proposed OpenSpec changes before committing them.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger guidance includes broad natural-language phrases such as "propose a change," "spec this out," and "open a change for X," which are common in ordinary conversation and could cause the skill to activate when the user did not explicitly intend to invoke OpenSpec. In this skill, unintended activation is moderately risky because it can steer the agent into creating or modifying project planning artifacts and using OpenSpec tools, potentially changing workflow state or generating repository files without clear user consent.

Static analysis

No suspicious patterns detected.