Amazon Sagemaker

• Outcome: Review
• Latest audit: May 29, 2026 at 9:36 PM UTC
• Version:
  1.0.2

Overview

This appears to be a real SageMaker integration, but it gives an agent broad authenticated cloud API access without clear guardrails for changes or deletions.

Install only if you are comfortable letting Membrane mediate authenticated SageMaker operations. Use a least-privilege AWS role, prefer non-production resources, review or pin the CLI version, and require manual approval before POST, PUT, PATCH, DELETE, endpoint, model, training-job, or other cost-impacting actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill description is broad enough to match generic requests about managing data or automating workflows, not just clearly scoped Amazon SageMaker tasks. Overbroad routing can cause the agent to invoke this skill in unintended contexts, leading to unnecessary external access, mistaken actions against the wrong service, or user confusion about what system is being operated.

VirusTotal

63/63 vendors flagged this skill as clean.