ClawHub
Back to skill

Security audit

design-brief

Security checks for vulnerabilities and agentic risk

Overview

This skill is a project design-brief workflow that reads local project context and writes a project-scoped spec file, with no evidence of hidden execution, exfiltration, or unrelated privilege use.

Install this if you want feature discussions to become written design briefs. Be aware that ordinary phrases like "how should we build" may invoke it, and it may create draft files in .claude/design-briefs/ during the workflow; review those files before committing or relying on them downstream.

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
Confidence
93% confidence
Finding
The trigger list is intentionally broad and includes common conversational phrases like 'brainstorm this', 'think through this feature with me', and 'how should we build'. In an agentic system, that can cause the skill to activate when the user did not intend to enter a formal design-brief workflow, which may redirect tasks, create files, or shape subsequent planning based on an unintended spec artifact.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The 'When to use this skill' examples repeat broad, natural-language phrases without enforcing tighter boundary checks. Because these phrases overlap with normal ideation or advisory requests, the skill may be invoked in ambiguous contexts and then proceed to write project files or steer workflow decisions that should have remained informal.

Static analysis

No suspicious patterns detected.