ClawHub
Back to skill

Security audit

sn-image-resume

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: turns user-provided resume text into a designed resume image using disclosed text and image generation tools.

Install only if you are comfortable with resume details being written temporarily to local /tmp storage and sent through the configured SenseNova/sn-image-base text and image services. Avoid including unnecessary sensitive personal data, and consider deleting the task directory after generation on shared systems.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly writes resume content and style instructions to predictable temporary files under /tmp, but the user-facing description does not warn that sensitive personal data will be persisted on disk during processing. Because resumes commonly contain PII such as names, emails, phone numbers, work history, and education details, undocumented disk persistence increases privacy and data-handling risk, especially on shared or multi-tenant systems.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill sends full resume content to external text-optimization and image-generation tools, but the description does not warn users that their personal data will leave the local agent context and be processed by downstream services. Since resumes often include sensitive PII and employment history, lack of transparency can cause unintended disclosure to third-party model providers or external gateways.

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:241