← back to git-land-main

SkillSpector · git-land-main

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

WARNINGmax severity: HIGHrisk score: 64

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, a…; Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain…; Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous …; +1 more

scanned 2026-08-22

Findings (8)

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.

scripts/install.sh

MEDIUMRogue Agentconfidence: 0.6

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/install.sh

HIGHTool Misuseconfidence: 0.75

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).

SKILL.md

HIGHTool Misuseconfidence: 0.75

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).

SKILL.md

HIGHTool Misuseconfidence: 0.65

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).

SKILL.md

HIGHTool Misuseconfidence: 0.75

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).

reference.md

HIGHTool Misuseconfidence: 0.65

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).

reference.md

HIGHYARA Matchconfidence: 0.75

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

reference.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

WARNINGthis skill

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete