← back to agentic-kaggle-skill

SkillSpector · agentic-kaggle-skill

independent scanner by NVIDIA · skill by FrankS-IntelLab · how it works ↗

FAILmax severity: CRITICALrisk score: 88

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, …; Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…; Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.; +1 more

scanned 2026-08-22

Findings (8)

LOWExcessive Agencyconfidence: 0.7

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

LICENSE

MEDIUMExcessive Agencyconfidence: 0.75

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

README.md

LOWSupply Chainconfidence: 0.6

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

requirements.txt

LOWSupply Chainconfidence: 0.6

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

requirements.txt

LOWSupply Chainconfidence: 0.6

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

requirements.txt

CRITICALSupply Chainconfidence: 0.9

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

requirements.txt

HIGHSupply Chainconfidence: 0.8

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

requirements.txt

CRITICALSupply Chainconfidence: 0.9

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

requirements.txt

What the verdicts mean

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

PASS

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete