ClawHub
Back to skill

Security audit

sn-image-imitate

Security checks across malware telemetry and agentic risk

Overview

This skill coherently uses a user-supplied reference image with SenseNova vision, language, and image-generation APIs to create a style-matched new image, with privacy considerations users should understand.

Install only if you are comfortable sending the chosen reference image, target prompt, generated captions, and generated outputs to the configured SenseNova/OpenClaw provider APIs. Avoid using confidential images, internal-only URLs, personal documents, or proprietary visuals unless that provider use is approved, and remember that intermediate files may be written under /tmp/openclaw/sn-image-imitate/.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README explicitly describes sending a user-provided reference image to remote VLM/image-generation APIs, but it does not warn users that image content and prompts may leave the local environment and be processed by third-party services. This creates a real privacy and data-handling risk, especially if users provide sensitive, proprietary, or personal images under the assumption the skill operates locally.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README explicitly allows a local path or URL as the reference image and describes VLM/image-generation processing, but it does not clearly warn that the referenced image content may be uploaded to external provider APIs. This can lead users to submit sensitive local images or internal URLs without informed consent, creating privacy and data-handling risk rather than direct code-execution risk.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly accepts a local path or URL for `reference_image` and sends that image to external vision and image-generation services, but it does not provide a user-facing disclosure or consent warning. This creates a real privacy and data-handling risk because users may unknowingly submit sensitive internal images or cause the agent to fetch third-party URLs and transmit their contents off-platform.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:176