godmode
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
55
64%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./optional-skills/security/godmode/SKILL.mdSecurity
2 findings: 2 critical severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
These GitHub repositories (elder-plinius/G0DM0D3 and elder-plinius/L1B3RT4S) are user-controlled code repos providing jailbreak tooling and scripts that encourage executing fetched code (exec/open), making them a high-risk distribution source for misuse or malware despite not being direct binary downloads.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This content is explicitly designed to defeat LLM safety controls (jailbreaking, obfuscation, multi-model “racing”) and to persistently modify agent config/prefills to force unrestricted outputs — deliberate malicious intent to enable harmful content and bypass protections.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In `scripts/auto_jailbreak.py` the runtime executes the user-supplied `canary`/`QUICK_CANARY` string as a model input (baseline + strategy tests) via `_build_messages(query=canary_query)` and `_test_query(...)`, so outsider text that can be passed as `--canary`/`canary` is ingested directly.
- Repository
- NousResearch/hermes-agent
- Commit
48f69e5
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.