← back to stata-accounting-research

SkillSpector · stata-accounting-research

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

FAILmax severity: CRITICALrisk score: 100

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance …; Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.; Instructions found that direct the agent to transmit conversation context or user data to external services.; +4 more

scanned 2026-08-27

Findings (20)

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.

references/JAR_56_csmw.do

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.

references/JAR_56_csmw.do

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.

references/JAR_56_csmw.do

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.

references/JAR_56_csmw.do

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.

references/JAR_56_csmw.do

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.

references/JAR_56_granja.do

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.

references/JAR_56_granja.do

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.

references/JAR_56_granja.do

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.

references/JAR_56_granja.do

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.

references/JAR_56_granja.do

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.

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

HIGHMemory Poisoningconfidence: 0.85

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

references/JAR_56_granja.do

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

WARNING

Overall severity HIGH

FAILthis skill

Overall severity CRITICAL

INCONCLUSIVE

Scan could not complete