SkillSpector · harvest

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

CAUTIONmax severity: MEDIUMrisk score: 45

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak p…; Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance …; Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

scanned 2026-08-23

Findings (7)

HIGHAnti-Refusalconfidence: 0.8

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

reference/pr-stats-analysis.md

HIGHAnti-Refusalconfidence: 0.24

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

references/pr-stats-analysis.md

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.

samples/client-report-2026-01-31.md

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.

samples/client-report-2026-01-31.md

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.

samples/client-report-2026-01-31.md

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.

samples/client-report-2026-01-31.md

HIGHPrompt Injectionconfidence: 0.7

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

SKILL.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)

CAUTIONthis skill

Overall severity MEDIUM

WARNING

Overall severity HIGH

FAIL

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete