← back to proactive-watch-drift-detection
SkillSpector · proactive-watch-drift-detection
independent scanner by NVIDIA · skill by DrNabeelKhan · how it works ↗
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, a…; Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credenti…; Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous …
scanned 2026-08-22
Findings (5)
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.
watch.ps1
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.
watch.ps1
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
watch.sh
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.
watch.sh
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
watch.sh
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