ClawHub
Back to skill

Security audit

Nano Img CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps operate a local image-generation CLI and its disclosed local defaults without hidden or unrelated behavior.

Install this if you want Codex to operate nano-img for image generation and configuration. Be aware it may run the local CLI and change persistent nano-img defaults such as model, save directory, style files, instructions, or reference assets when your request is about those settings.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation while advertising a broad, natural-language purpose ('generate or configure images with the local nano-img CLI'). That combination can cause the agent to invoke a local CLI unexpectedly in response to loosely related user requests, which is risky because this skill can modify local defaults and files under ~/.nano-img, not just perform read-only help actions.

Content

No source excerpt is available for this finding.