microsoft-foundry
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, customize deployment, onboard, availability, fine-tune, SFT, DPO, RFT, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
Security Findings
Flagged by the hosting marketplace
the skills.sh security audit flagged this skill (status=warn, risk=medium) — flagged by Snyk,ZeroLeaks
User-input→dynamic-exec taint flow
User input reaches dynamic-exec sink ``exec`` in ``load_grader`` (line 54)
Low-reputation package
Package 'azure-ai-agentserver-optimization' (pip) has weak reputation: published 42 days ago (< 90d)
Low-reputation package
Package 'agent-framework-foundry-hosting' (pip) has weak reputation: published 84 days ago (< 90d)
Versions
5- Scanned Jul 19, 2026, 10:01 AM30High Risk
- Scanned Jun 1, 2026, 05:51 AM100Clean
- Scanned May 6, 2026, 06:38 PM94Clean
- Scanned Apr 28, 2026, 04:52 PMClean
- Scanned Apr 7, 2026, 02:00 PMClean