SkillSpector · lobster

independent scanner by NVIDIA · skill by aniruddhaadak80 · how it works ↗

CAUTIONmax severity: MEDIUMrisk score: 27

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance …; Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

scanned 2026-08-23

Findings (2)

MEDIUMMemory Poisoningconfidence: 0.8

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

SKILL.md

HIGHPrivilege Escalationconfidence: 0.6

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

src/lobster-runner.ts

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)

CAUTIONthis skill

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete