product-to-ads
What this skill does
Generate professional advertising images from product URLs using an AI pipeline on ComfyDeploy
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=product-to-adsAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/generate.py
API_BASE = 'https://api.comfydeploy.com/api' - this is a third-party API endpoint that could be used to exfiltrate data or control the agent remotely if not properly secured.Insecure Configuration
Insecure Configuration via local-llm-review
scripts/generate.py
BRANDS_DIR = Path.home() / 'claw' - this path is incomplete and may point to an insecure or untrusted location, potentially exposing user data.Badge
Add the Anomity scan badge for product-to-ads to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of product-to-ads? Report an issue or request a rescan.
