deepread-ocr
What this skill does
Document processing and OCR API for AI agents, providing structured data extraction with confidence scoring and Human-in-the-Loop review.
github/leoyeai - Information Disclosure - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=deepread-ocrAssessments (2)
Information Disclosure
Information Disclosure via local-llm-review
SKILL.md
The skill's metadata includes a homepage URL: 'https://www.deepread.tech'. While this is a legitimate URL, it could be considered a potential risk if the domain is not fully controlled or verified by Information Disclosure via local-llm-review
package.json
The package.json file includes a homepage URL: 'https://www.deepread.tech' and a repository URL: 'https://github.com/deepread-tech/deep-read-service'. These are legitimate URLs but could be flagged asBadge
Add the Anomity scan badge for deepread-ocr 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 deepread-ocr? Report an issue or request a rescan.
