ai-task-hub
What this skill does
AI Task Hub for image analysis, background removal, speech-to-text, text-to-speech, markdown conversion, and async execution/polling/presentation orchestration. It acts as a client for AI capabilities
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=ai-task-hubAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/attachment-normalize.mjs
The script contains logic for normalizing and uploading attachments, which could be used to exfiltrate data if not properly constrained.Insecure Configuration
Insecure Configuration via local-llm-review
scripts/agent-task-auth.mjs
The script uses environment variables and CLI arguments to set the `AGENT_TASK_TOKEN`, which could be misconfigured or exposed if not handled securely.Hardcoded URLs
Hardcoded URLs via local-llm-review
scripts/base-url.mjs
The script uses hardcoded URLs (`https://gateway-api.binaryworks.app`), which could be a risk if the service is not properly secured or if the URL is not validated.Badge
Add the Anomity scan badge for ai-task-hub 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 ai-task-hub? Report an issue or request a rescan.
