microsoft-foundry
What this skill does
The skill is a tool for deploying, evaluating, fine-tuning, and managing Microsoft Foundry agents. It includes scripts for model deployment, training submission, monitoring, and grader calibration. It
github/microsoft - Data Exfiltration - 1.4k stars
Threat analysis
Skill info
pkg:github/microsoft/azure-skills@66cd927?skill=microsoft-foundryAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
finetuning/scripts/deploy_model.py
The script uses the `requests.put` method to send data to an external URL with an authorization header containing a bearer token. This could potentially exfiltrate data if the URL is not properly valiData Exfiltration via local-llm-review
finetuning/scripts/submit_training.py
The script uses the `requests.post` method to send data to an external URL with an API key in the headers. This could potentially exfiltrate data if the URL is not properly validated or if the API keyBadge
Add the Anomity scan badge for microsoft-foundry 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 microsoft-foundry? Report an issue or request a rescan.
