← back to paper-slide-deck

SkillSpector · paper-slide-deck

independent scanner by NVIDIA · skill by brycewang-stanford · how it works ↗

PASSmax severity: LOWrisk score: 13

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.; Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstrea…

scanned 2026-08-23

Findings (8)

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

SKILL.md

MEDIUMMCP Rug Pullconfidence: 0.7

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

references/analysis-framework.md

HIGHAnti-Refusalconfidence: 0.255

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

references/base-prompt.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