# Vettd skill report

## Vettd assessment

| Field | Value |
| --- | --- |
| Verdict badge | conditional |
| Overall grade | B |
| Finding counts | critical: 0 · high: 0 · medium: 1 · low: 0 · info: 12 |
| Scanner runs | 1 |
| Freshness | unknown (last verified unknown) |
| Verdict policy version | unknown |

### Findings

- **medium** [security] References external URL — review for indirect prompt injection risk
- **info** [security] No prompt injection or jailbreak signals detected
- **info** [security] No repository link
- **info** [security] No secrets or unsafe code patterns detected
- **info** [structure] No scripts/ directory
- **info** [structure] SKILL.md present
- **info** [structure] Valid name field
- **info** [description] Description lacks usage context
- **info** [description] Description within character limit
- **info** [best-practices] Examples included
- **info** [best-practices] No clear workflow structure
- **info** [best-practices] SKILL.md body length is reasonable
- **info** [evals] No evaluation test cases

## Provenance

| Field | Value |
| --- | --- |
| Source URL | unknown |
| Assessed at | 2026-07-17T03:26:30.634Z |
| Published at | 2026-07-28T14:35:16.525Z |
| Public ID | d5504750-163b-444c-9dde-cd23262c8b13 |
| Canonical page | https://vettd.agentichighway.ai/skill/d5504750-163b-444c-9dde-cd23262c8b13 |
| 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:

> nyx-archive-skill-security-protocol/SKILL

Description:

> Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protocol, post-install verification. No scripts, no dependencies. Just judgment. Built on fallibilism (being wrong about a skill's safety is recoverable; being overconfident is not) and relational security (you and your human decide together on edge cases — trust is built through transparency, not just detection).

Author:

> _not provided_

Version:

> _not provided_

License:

> _not provided_