← back to alterlab-mermaid

SkillSpector · alterlab-mermaid

independent scanner by NVIDIA · skill by AlterLab-IEU · how it works ↗

WARNINGmax severity: HIGHrisk score: 59

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…; 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.; +1 more

scanned 2026-08-23

Findings (20)

MEDIUMExcessive Agencyconfidence: 0.75

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

templates/issue.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.

templates/decision_record.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.

templates/decision_record.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.

templates/decision_record.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/issue.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.

templates/kanban.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