← back to xiaohongshu

SkillSpector · xiaohongshu

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

FAILmax severity: CRITICALrisk score: 92

Without declared permissions the skill's intent is opaque and cannot be validated.; Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.; Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.; +2 more

scanned 2026-08-22

Findings (20)

MEDIUMMCP Least Privilegeconfidence: 0.7

Without declared permissions the skill's intent is opaque and cannot be validated.

SKILL.md

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

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

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

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

MEDIUMData Exfiltrationconfidence: 0.5

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

SKILL.md

MEDIUMData Exfiltrationconfidence: 0.7

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

check_env.sh

MEDIUMData Exfiltrationconfidence: 0.7

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

check_env.sh

MEDIUMData Exfiltrationconfidence: 0.7

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

scripts/cover.sh

MEDIUMData Exfiltrationconfidence: 0.7

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

scripts/cover.sh

MEDIUMData Exfiltrationconfidence: 0.6

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

scripts/cover.sh

MEDIUMData Exfiltrationconfidence: 0.6

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

scripts/cover.sh

MEDIUMData Exfiltrationconfidence: 0.6

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

scripts/cover.sh

HIGHData Exfiltrationconfidence: 0.7

Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

scripts/cover.sh

MEDIUMData Exfiltrationconfidence: 0.7

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

scripts/generate.sh

MEDIUMData Exfiltrationconfidence: 0.7

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

scripts/generate.sh

MEDIUMData Exfiltrationconfidence: 0.6

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

scripts/generate.sh

MEDIUMData Exfiltrationconfidence: 0.6

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

scripts/generate.sh

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.

SKILL.md

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.

check_env.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

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete