microsoft-foundry
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: 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, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, agent monitoring, 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).
61
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugin/skills/microsoft-foundry/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). The skill's Hosted Agent creation workflow explicitly instructs the agent to browse and download public GitHub sample files (see foundry-agent/create/create-hosted.md Step 3–4 with GET https://api.github.com/repos/... and curl/gh download commands) and to read the sample README and code, which means it ingests and acts on external public repository content that could contain untrusted instructions influencing subsequent implementation, configuration, or deployment steps.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill instructs downloading and installing a preview Python wheel directly at runtime from an external GitHub raw URL (https://github.com/Zyysurely/tool/raw/main/preview/azure_ai_agentserver_optimization-1.0.0b1.dev1-py3-none-any.whl), which would execute remote code as a required dependency and can directly control agent prompts via the optimization SDK (load_config), so this is a high-confidence runtime risk.
- Repository
- microsoft/github-copilot-for-azure
- Commit
915f809
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.