ClawHub
Back to skill

Security audit

Demo Production

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent demo-building workflow with disclosed autonomy, review gates, and no evidence of hidden execution, persistence, credential handling, or exfiltration.

Install this if you want a coding agent to take more initiative when turning rough ideas into demos. Review assumptions before approving Stage 4, especially for sensitive domains or anything involving real infrastructure, auth, billing, compliance, or production data.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (3)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 289)May include surrounding context.

md
- Use realistic mock content.
- Include important states, not just the happy path.
- Visually communicate the intended product experience.
- Make incomplete functionality feel intentional through simulation or clear state changes.

Prototype techniques may include:

Memory Manipulation

High
Category
Memory Poisoning
Confidence
90% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 483)May include surrounding context.

md
- [ ] Empty data state renders cleanly.
- [ ] Long text or overflow does not break layout.
- [ ] Invalid input is handled with visible feedback.
- [ ] Repeated clicks on primary actions do not corrupt state.
- [ ] Loading or pending state is visible where async work happens.
- [ ] Failure path shows recoverable UI, not a crash.
- [ ] Small viewport, 375px width or equivalent, remains usable on the main screen.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises itself with very broad trigger phrases covering nearly any request to create, plan, prototype, or build a product demo. That can cause over-invocation and route unrelated or sensitive requests into an autonomy-heavy workflow that infers missing details and may browse or build without sufficient scoping. In context, this is more dangerous because the skill explicitly minimizes user prompting and encourages autonomous continuation through multiple stages.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.