ClawHub
Back to skill

Security audit

Flow Image Gen

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends storyboard prompts to Google Gemini to create image files in a job folder.

Install only if you are comfortable sending image prompts and style details from input.json to Google Gemini using your GEMINI_API_KEY. Avoid putting sensitive, proprietary, or regulated content in those prompts unless that use is approved for your account and project.

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 (1)

External Transmission

Medium
Category
Data Exfiltration
Content
local attempt
  for attempt in 1 2; do
    CODE=$(curl -sS -X POST "$ENDPOINT" \
      -H "x-goog-api-key: $GEMINI_API_KEY" \
      -H "Content-Type: application/json" \
      -d @"$REQ" -w "%{http_code}" -o "$RESP")
Confidence
91% confidence
Finding
The script transmits prompt content, style anchors, and color-grade data from the job input to an external Google API using curl. In this skill context that is expected functionality, but it is still a real data-exfiltration boundary: if input.json contains sensitive or proprietary material, that data leaves the local environment without any minimization, allowlisting, or sensitivity checks.

Static analysis

No suspicious patterns detected.