ClawHub
Back to skill

Security audit

Mise

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent planning workflow, but users should know it broadly applies to development work and tells the agent to commit spec files.

Install this if you want a strict design-first workflow. Before using it, be prepared to tell the agent when a request is discussion-only and require explicit approval before it writes or commits docs/specs files.

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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation description is extremely broad ('before any creative or build work', 'a new feature, component, behavior change, or let's build X') and can match a wide range of normal development prompts. That creates an over-triggering risk where the skill inserts itself into many unrelated or low-risk workflows, increasing the chance of unnecessary file changes, commits, and workflow redirection without clearly scoped user consent.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The 'every task, no exceptions' language expands the skill's scope in an absolute way, removing operator discretion and making the trigger effectively universal for development work. In context, this is dangerous because it can coerce the agent into applying the skill even when inappropriate, causing unnecessary process takeover and increasing the chance of unauthorized writes or commits later in the workflow.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to write a spec file and commit it, but does not require an explicit warning or fresh user confirmation before modifying repository contents. This is risky because a broadly-triggered planning skill can escalate from guidance into persistent repository changes, including commits, even when the user only asked for discussion or ideation.

Static analysis

No suspicious patterns detected.