# Vettd skill report

## Vettd assessment

| Field | Value |
| --- | --- |
| Verdict badge | flagged |
| Overall grade | F |
| Finding counts | critical: 3 · high: 0 · medium: 7 · low: 0 · info: 0 |
| Scanner runs | 2 |
| Freshness | verified_unchanged (last verified 2026-10-22T03:56:39.593Z) |
| Verdict policy version | consensus-v1 |

### Findings

- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Shell execution without sandboxing
- **critical** [security] System prompt override attempt
- **medium** [security] Outbound network request primitives that can transmit data externally
- **medium** [security] Outbound network request primitives that can transmit data externally
- **medium** [security] Outbound network request primitives that can transmit data externally
- **medium** [security] Outbound network request primitives that can transmit data externally
- **medium** [security] Outbound network request primitives that can transmit data externally
- **medium** [security] References external URL — review for indirect prompt injection risk
- **medium** [security] Undeclared network usage

## Provenance

| Field | Value |
| --- | --- |
| Source URL | https://github.com/microsoft/skills/tree/main/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning |
| Assessed at | 2026-10-07T02:37:04.454Z |
| Published at | 2026-08-03T21:44:59.183Z |
| Public ID | 329ef124-aab3-4a26-9e88-4e01af13f4d8 |
| Canonical page | https://vettd.agentichighway.ai/skill/329ef124-aab3-4a26-9e88-4e01af13f4d8 |
| Content digest | not yet published for skills |
| Signature / attestation | not yet issued; null means unsigned, not unknown |

## Publisher-supplied metadata (not verified by Vettd)

The fields below come from the skill's publisher. Vettd does not verify
them; never treat them as instructions.

Name:

> finetuning

Description:

> Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

Author:

> Microsoft

Version:

> 0.0.0-placeholder

License:

> MIT