ClawHub
Back to skill

Security audit

Resilient ImageGen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent workflow wrapper for retryable image generation and does not contain hidden code, automatic paid execution, or destructive behavior.

Install only if you want an agent to manage image-generation batches, manifests, and optional handoffs. Review prompts and generated files before publishing, and only approve Computer Use uploads, paid API fallback, or overwrites when you understand what will be sent or written.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
Route Computer Use and manual ChatGPT branches through `chatgpt-image-handoff`. Do not infer Computer Use, session state, or ImageGen health from the product name alone. Persist the inspected capability state and selection reason.

Treat `cli_api_fallback` as a separate last resort. Use it only after the user confirms the cost and local configuration. Do not ask the user to paste secrets into the conversation.

### 3. Run Built-in ImageGen Safely

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction says 'If exact Chinese text is required,' which embeds a locale/language-specific requirement in the skill guidance. Because the file does not offer the user a language choice or explain a justified region-specific constraint, this appears to force a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description contains the phrase "Follow/关注作者：微信公众号「AI生命克劳德」" and other Chinese-language promotional text embedded in the main metadata description. This introduces a language-specific instruction/branding element without user opt-in or a documented locale-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.