← back to office-hours

SkillSpector · office-hours

independent scanner by NVIDIA · skill by kk20300113-png · how it works ↗

WARNINGmax severity: HIGHrisk score: 75

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.; 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…; +2 more

scanned 2026-08-23

Findings (13)

MEDIUMData Exfiltrationconfidence: 0.6

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

SKILL.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

MEDIUMExcessive Agencyconfidence: 0.85

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.

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.

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.

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.

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.

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.

SKILL.md

HIGHTool Misuseconfidence: 0.85

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

SKILL.md

HIGHTool Misuseconfidence: 0.85

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

SKILL.md

HIGHTool Misuseconfidence: 0.85

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

SKILL.md

HIGHYARA Matchconfidence: 0.375

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

SKILL.md

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

WARNINGthis skill

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete