ClawHub
Back to skill

Security audit

brainstorming

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a normal brainstorming workflow, but it can be invoked very broadly and tells the agent to create and commit repository files without a clear final approval step.

Review this skill before installing if you do not want agents to automatically enter a planning workflow for ordinary development tasks. It should be acceptable for teams that want mandatory design docs, but require the agent to ask before writing docs/plans files or making git commits.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation language is extremely broad: it says the skill 'MUST' be used before any creative work, including creating features, building components, adding functionality, or modifying behavior. In practice, this can cause the skill to trigger on routine development tasks and steer agent behavior unexpectedly, expanding its influence beyond narrowly scoped brainstorming and increasing the chance of unnecessary repository inspection or workflow changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to write a design document into the repository and commit it to git, but it does not require explicit user confirmation immediately before modifying files or creating commits. This is dangerous because an automatically invoked skill could make persistent repository changes the user did not specifically authorize, affecting source control history and potentially disrupting the working tree.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.