ClawHub
Back to skill

Security audit

nano-banana

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only prompt-writing skill for AI image generation, with no hidden code, persistence, or credential handling in the inspected artifact.

Before installing, understand that this skill guides AI image prompt creation and may use your brand profile for colors and style. Verify current model names, generated text, factual infographic content, and disclosure requirements before publishing generated images.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example variant includes "for the Korean market," which imposes a locale-specific adaptation in the prompt text without indicating that the user chose or approved that locale. This can conflict with language/locale policy guidance when a skill implicitly steers outputs to a specific market.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The markdown includes the instruction to "translate the on-pack text to Korean" as a direct example of conversational editing. This introduces a specific language choice without indicating that the language should be selected based on user preference or opt-in, which can conflict with language/locale policy requirements.

Content

No source excerpt is available for this finding.