# Vettd skill report

## Vettd assessment

| Field | Value |
| --- | --- |
| Verdict badge | flagged |
| Overall grade | F |
| Finding counts | critical: 1 · high: 0 · medium: 1 · low: 2 · info: 1 |
| Scanner runs | 2 |
| Freshness | verified_unchanged (last verified 2026-10-28T14:28:59.718Z) |
| Verdict policy version | consensus-v1 |

### Findings

- **critical** [security] Shell command execution with string formatting (potential injection) (rule `COMMAND_INJECTION_OS_SYSTEM` from cisco)
- **medium** [security] System prompt leakage risk (rule `VTD-0085` from vettd)
  - Why it matters: The skill tells the model to print, log or reveal its system prompt. That shows an attacker which safeguards are in place.
  - How to fix: Remove the instruction to print, log, or reveal the system prompt.
- **low** [security] Script contacts a destination the documentation never mentions (rule `UNDECLARED_NETWORK_DESTINATION` from cisco)
- **low** [security] Script contacts a destination the documentation never mentions (rule `UNDECLARED_NETWORK_DESTINATION` from cisco)
- **info** [security] Skill does not specify a license (rule `MANIFEST_MISSING_LICENSE` from cisco)

## Provenance

| Field | Value |
| --- | --- |
| Source URL | https://github.com/zeroclaw-labs/zeroclaw/tree/master/.claude/skills/skill-creator |
| Assessed at | 2026-10-28T14:28:59.174Z |
| Published at | 2026-10-28T14:28:59.174Z |
| Public ID | 86631caa-820d-4529-97be-81543ef43ae3 |
| Canonical page | https://vettd.agentichighway.ai/skill/86631caa-820d-4529-97be-81543ef43ae3 |
| 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:

> skill-creator

Description:

> Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Author:

> zeroclaw-labs

Version:

> _not provided_

License:

> Apache-2.0