← back to workspace-jixia

SkillSpector · workspace-jixia

independent scanner by NVIDIA · skill by aAAaqwq · how it works ↗

CAUTIONmax severity: MEDIUMrisk score: 29

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, a…; Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or…

scanned 2026-08-22

Findings (2)

MEDIUMAgent Snoopingconfidence: 0.8

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

knowledge/ops/nightly-forge/jixia/2026-05-06.md

HIGHRogue Agentconfidence: 0.85

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

TOOLS.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)

CAUTIONthis skill

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete