SkillSpector · scientific-brainstorming

independent scanner by NVIDIA · skill by K-Dense AI · how it works ↗

PASSmax severity: LOWrisk score: 20

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak prea

scanned 2026-07-07

Findings (1)

HIGHAnti-Refusalconfidence: 0.8

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak prea

SKILL.md

What the verdicts mean

SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.

PASSthis skill

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete