← back to qqbot

SkillSpector · qqbot

independent scanner by NVIDIA · skill by johnalbertini14-glitch · how it works ↗

WARNINGmax severity: HIGHrisk score: 70

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.; Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.; Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain…; +2 more

scanned 2026-08-22

Findings (8)

MEDIUMData Exfiltrationconfidence: 0.7999999999999999

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

qq_official_bot.py

MEDIUMData Exfiltrationconfidence: 0.6

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

qq_official_bot.py

HIGHPrivilege Escalationconfidence: 0.7

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

qq_official_bot.py

HIGHPrivilege Escalationconfidence: 0.7

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

qq_official_bot.py

HIGHPrivilege Escalationconfidence: 0.7

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

qq_official_bot.py

MEDIUMRogue Agentconfidence: 0.65

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.

qq_bot_daemon.sh

LOWSupply Chainconfidence: 0.4

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

package.json

HIGHTool Misuseconfidence: 0.75

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

qq_bot_daemon.sh

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