SkillSpector · quality-manager-qmr

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

PASSmax severity: LOWrisk score: 15

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance …; 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 (5)

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

SKILL.md

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

SKILL.md

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

SKILL.md

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

SKILL.md

MEDIUMRogue Agentconfidence: 0.75

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.

scripts/quality_effectiveness_monitor.py.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