SkillMD SkillMD
light-dark-mode
Profile My skills Saved Collections Edit profile Submit a skill

← back to decision-log

SkillSpector · decision-log

independent scanner by NVIDIA · skill by heath-gtm · how it works ↗

PASSmax severity: LOWrisk score: 13

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…; Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain…

scanned 2026-08-23

Findings (3)

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

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.

SKILL.md

MEDIUMRogue Agentconfidence: 0.6

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

README.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