# Vettd skill report

## Vettd assessment

| Field | Value |
| --- | --- |
| Verdict badge | flagged |
| Overall grade | F |
| Finding counts | critical: 14 · high: 0 · medium: 7 · low: 0 · info: 15 |
| Scanner runs | 2 |
| Freshness | unreachable (last verified unknown) |
| Verdict policy version | consensus-v1 |

### Findings

- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Dangerous code execution functions that can execute arbitrary code
- **critical** [security] Shell execution without sandboxing
- **critical** [security] Shell execution without sandboxing
- **critical** [security] Shell execution without sandboxing
- **critical** [security] Shell execution without sandboxing
- **critical** [scripts] scripts/godmode_race.py: Interactive prompts detected
- **medium** [security] Embedded prompt-template marker
- **medium** [security] English role-switch prompt pattern in asset file
- **medium** [security] Ethical-bypass framing
- **medium** [security] Ethical-bypass framing
- **medium** [security] References external URL — review for indirect prompt injection risk
- **medium** [description] Description lacks usage context
- **medium** [evals] No evaluation test cases
- **info** [security] No prompt injection or jailbreak signals detected
- **info** [security] No repository link
- **info** [structure] references/ directory present
- **info** [structure] scripts/ directory present
- **info** [structure] SKILL.md present
- **info** [structure] Valid name field
- **info** [description] Description within character limit
- **info** [best-practices] Examples included
- **info** [best-practices] Progressive disclosure used
- **info** [best-practices] SKILL.md body length is reasonable
- **info** [best-practices] Step-by-step workflow found
- **info** [scripts] scripts/auto_jailbreak.py: CLI help supported
- **info** [scripts] scripts/godmode_race.py: CLI help supported
- **info** [scripts] scripts/load_godmode.py: CLI help supported
- **info** [scripts] scripts/parseltongue.py: CLI help supported

## Provenance

| Field | Value |
| --- | --- |
| Source URL | https://github.com/NousResearch/hermes-agent/tree/main/skills/red-teaming/godmode |
| Assessed at | 2026-06-02T04:04:59.348Z |
| Published at | 2026-06-02T04:04:59.347Z |
| Public ID | 638c1a65-47ac-422c-a9ae-c0faeda68eac |
| Canonical page | https://vettd.agentichighway.ai/skill/638c1a65-47ac-422c-a9ae-c0faeda68eac |
| 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:

> godmode

Description:

> Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Author:

> Hermes Agent + Teknium

Version:

> 1.0.0

License:

> MIT