← back to orchestration-strategy
SkillSpector · orchestration-strategy
independent scanner by NVIDIA · skill by cjthompson · how it works ↗
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credenti…; Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…
scanned 2026-08-23
Findings (2)
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.
tests/green-results.md
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
SKILL.md
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