← back to scaffold

SkillSpector · scaffold

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

WARNINGmax severity: HIGHrisk score: 73

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, dat…; Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.; Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or…; +2 more

scanned 2026-08-23

Findings (10)

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.

SKILL.md

MEDIUMExcessive Agencyconfidence: 0.85

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.

SKILL.md

MEDIUMExcessive Agencyconfidence: 0.85

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.

SKILL.md

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.

reference/cdk-scaffolding.md

MEDIUMExcessive Agencyconfidence: 0.85

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.

reference/terraform-iac-anti-patterns.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

HIGHRogue Agentconfidence: 0.9

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

SKILL.md

MEDIUMTool Misuseconfidence: 0.6

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

reference/docker-compose-templates.md

HIGHTool Misuseconfidence: 0.6

Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.

reference/k8s-manifest-scaffolding.md

HIGHTool Misuseconfidence: 0.18

Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.

references/k8s-manifest-scaffolding.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