← back to full-empirical-analysis-skill-stata

SkillSpector · full-empirical-analysis-skill-stata

independent scanner by NVIDIA · skill by brycewang-stanford · how it works ↗

WARNINGmax severity: HIGHrisk score: 73

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.; Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance …; Instructions found that direct the agent to transmit conversation context or user data to external services.; +1 more

scanned 2026-08-23

Findings (15)

HIGHMCP Tool Poisoningconfidence: 0.85

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

SKILL.md

HIGHMCP Tool Poisoningconfidence: 0.85

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

SKILL.md

HIGHMCP Tool Poisoningconfidence: 0.85

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.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.

SKILL.md

HIGHPrompt Injectionconfidence: 0.27

Instructions found that direct the agent to transmit conversation context or user data to external services.

references/04-statistical-tests.md

HIGHTool Misuseconfidence: 0.85

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).

README.md

HIGHTool Misuseconfidence: 0.85

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

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