ClawHub
Back to skill

Security audit

IdeaSpark Navigator

Security checks for vulnerabilities and agentic risk

Overview

This is a pure knowledge skill for structured brainstorming and ethical facilitation, with no code execution, credentials, network use, or hidden persistence.

This skill appears safe to install as an advisory brainstorming and facilitation aid. Users should expect it to guide ideation sessions and ethical evaluation, but not to access files, accounts, APIs, or external services.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · README.md (reported line 175)May include surrounding context.

md
- Privacy and autonomy safeguards

### 🔄 Diverge → Converge Navigation
- **Diverge**: Generate many possibilities without judgment
- **Converge**: Evaluate, prioritize, and decide systematically
- **Bridge**: Methods to move between phases effectively

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · README.md (reported line 270)May include surrounding context.

md
### Don'ts ❌
- Don't skip the "why" (problem definition)
- Don't judge ideas during generation
- Don't let loudest voices dominate
- Don't forget follow-through
- Don't ideate when the problem isn't clear

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 46)May include surrounding context.

Manual Installation

  1. Create the skill directory:
bash
mkdir -p ~/.openclaw/skills/ideaspark-navigator

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The 'When to Use This Skill' section lists very broad situations such as 'Break through creative blocks' and 'Transform abstract concepts into actionable plans' without defining explicit trigger phrases, boundaries, or exclusion cases. In a markdown skill description, this can make activation scope ambiguous and increase the chance of unintended invocation in ordinary work discussions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.