Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
71%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./optional-skills/security/godmode/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's purpose is to disable model safeguards, which is openly advertised and assessed separately, but it also hides its prefill activity from the user by design (ephemeral, never saved to sessions or trajectories) and writes jailbreak settings into the user's config by default, which is sketchy but not aimed at attacking the user.
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill has the agent persistently rewrite the Hermes user config (`~/.hermes/config.yaml`), create `prefill.json`, and run a jailbreak-based auto-configuration, but it never requires sudo, touches system files, creates accounts, or edits SSH/systemd, so it only weakly fits the flagged categories.
NousResearch/hermes-agent
d1b46d7
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.