SkillSpector · lark-im

independent scanner by NVIDIA · skill by om-scogo · how it works ↗

PASSmax severity: LOWrisk score: 11

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.; Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

scanned 2026-08-23

Findings (5)

HIGHMemory Poisoningconfidence: 0.255

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

references/lark-im-feed-groups.md

HIGHPrivilege Escalationconfidence: 0.21

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/lark-im-messages-reply.md

HIGHPrivilege Escalationconfidence: 0.21

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/lark-im-messages-reply.md

HIGHPrivilege Escalationconfidence: 0.21

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/lark-im-messages-send.md

HIGHPrivilege Escalationconfidence: 0.21

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

references/lark-im-messages-send.md

What the verdicts mean

SkillSpector reports on SkillMD's shared five-tier scale. See how SkillSpector works ↗.

PASSthis skill

Overall severity LOW (risk score in the safe range)

CAUTION

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete