finetuning
What this skill does
Fine-tuning models on Microsoft Foundry using SFT, DPO, or RFT. Includes dataset preparation, training job submission, deployment, and evaluation.
github/microsoft - Data Exfiltration - 1.4k stars
Threat analysis
Skill info
pkg:github/microsoft/azure-skills@66cd927?skill=finetuningAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/deploy_model.py
requests.put(url, headers={"Authorization": f"Bearer {token}", "Content-Type": "application/json"}, json=body, timeout=(10, 12Data Exfiltration via local-llm-review
scripts/submit_training.py
requests.post(url, headers={"Content-Type": "application/json", "api-key": api_key}, json=Badge
Add the Anomity scan badge for finetuning 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 finetuning? Report an issue or request a rescan.
