ClawHub
Back to skill

Security audit

design-brief

Security checks for vulnerabilities and agentic risk

Overview

This skill is a project-design workflow that reads nearby project context and writes a design brief, with no evidence of hidden execution, exfiltration, or destructive behavior.

Install this if you want the agent to formalize feature ideas into project design briefs. Expect it to read relevant project files and create or update .claude/design-briefs entries; use an explicit /design-brief request if you want to avoid accidental activation from broad brainstorming phrases.

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 skill advertises auto-trigger phrases such as "brainstorm this," "think through this feature with me," and "how should we build," which are common conversational phrases and may cause the skill to activate when the user did not intend to enter a formal design-brief workflow. In an agentic system, unintended invocation can redirect the session into file reads/writes and multi-phase questioning, creating workflow confusion, unnecessary repository access, and incorrect routing away from the user’s actual task.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Although the file lists some exclusions, the routing guidance still depends on subjective judgments like whether a task has a "clear spec" or whether the user wants to "design this first," leaving substantial ambiguity in when the skill should take control. That ambiguity increases the chance of misclassification and accidental execution of this workflow in place of more appropriate skills, especially when other skills are instructed to route undecided or architectural work here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.