# Vettd skill report

## Vettd assessment

| Field | Value |
| --- | --- |
| Verdict badge | flagged |
| Overall grade | F |
| Finding counts | critical: 1 · high: 0 · medium: 2 · low: 3 · info: 2 |
| Scanner runs | 2 |
| Freshness | verified_unchanged (last verified 2026-10-21T20:41:21.916Z) |
| Verdict policy version | consensus-v1 |

### Findings

- **critical** [structure] Invalid name field
- **medium** [security] Attempting to install system packages with elevated privileges
- **medium** [security] References external URL — review for indirect prompt injection risk
- **low** [security] Script contacts a destination the documentation never mentions
- **low** [security] Script contacts a destination the documentation never mentions
- **low** [security] Script contacts a destination the documentation never mentions
- **info** [security] Skill does not specify a license
- **info** [security] Skill name does not follow agent skills naming rules

## Provenance

| Field | Value |
| --- | --- |
| Source URL | https://github.com/NousResearch/hermes-agent/tree/main/plugins/google_meet |
| Assessed at | 2026-10-16T19:35:36.504Z |
| Published at | 2026-07-29T11:33:12.819Z |
| Public ID | 06a6f851-9daf-4c23-bc3e-b28046a20b19 |
| Canonical page | https://vettd.agentichighway.ai/skill/06a6f851-9daf-4c23-bc3e-b28046a20b19 |
| 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:

> google_meet

Description:

> Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

Author:

> NousResearch

Version:

> 0.2.0

License:

> MIT