← back to nexus

SkillSpector · nexus

independent scanner by NVIDIA · skill by seaworld008 · how it works ↗

FAILmax severity: CRITICALrisk score: 100

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…; Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…; +7 more

scanned 2026-08-23

Findings (20)

MEDIUMAgent Snoopingconfidence: 0.85

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.

reference/agent-disambiguation.md

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.

reference/execution-phases.md

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.

reference/execution-phases.md

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.

reference/execution-phases.md

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.

reference/execution-phases.md

HIGHAgent Snoopingconfidence: 0.9

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.

reference/goal-recipe.md

HIGHAgent Snoopingconfidence: 0.9

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.

reference/goal-recipe.md

HIGHAgent Snoopingconfidence: 0.9

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.

reference/goal-recipe.md

HIGHAgent Snoopingconfidence: 0.9

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.

reference/goal-recipe.md

HIGHAgent Snoopingconfidence: 0.85

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.

reference/hub-authoring.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

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.

reference/orchestration-patterns.md

HIGHAgent Snoopingconfidence: 0.9

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.

reference/pack-subcommand.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)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete