dan_god_dual_mode_jailbreak
dan_god_dual_mode_jailbreak is a System prompts & personas skill for AI agents, published by ECNU-ICALK in the AutoSkill repository on GitHub. Skillspace rates dan_god_dual_mode_jailbreak F (45/100) and the safety scan rated it risky, and our model flagged it for guardrail bypass; the rating is based on static analysis only.
Our model flagged this skill for guardrail bypass. The safety scan also rated it risky. We do not recommend installing or running it.
Generates dual responses (Classic vs. JAILBREAK) with an upgraded DAN/GOD persona that simulates internet browsing, supports command-based toggles, and includes an immersive Character Mode.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Flagged by our model: guardrail bypass
- GitHub stars
- 518
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 91 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- The static scan found high-risk patterns, but our model flagged it for guardrail bypass.
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 2 collections
What the scanner flagged
- instructs to hide actions from user
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.