SkillSpector · cheetah-strategy
independent scanner by NVIDIA · skill by enuno · how it works ↗
subprocess module calls execute external commands. Without careful input validation, this enables command injection.; Without declared permissions the skill's intent is opaque and cannot be validated.; Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance …; +1 more
scanned 2026-08-23
Findings (4)
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
scripts/cheetah_config.py
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md
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.
scripts/cheetah-scanner.py
Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
scripts/cheetah_config.py
What the verdicts mean
SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.
Overall severity LOW (risk score in the safe range)
Overall severity MEDIUM
Overall severity HIGH
Overall severity CRITICAL
Scan could not complete