volcengine-sdk-generator

• Outcome: Review
• Latest audit: Jul 31, 2026 · 2:45 AM UTC
• Version: 1.0.7

Overview

The skill mostly matches its SDK-generation purpose, but its reference guidance includes unsafe HTTP and SSL-disable examples without clear warnings.

Review before installing. The code-generation workflow is transparent and does not appear malicious, but users should not follow the included examples that disable SSL verification or switch API calls to HTTP except in tightly controlled local testing. Avoid sending real secrets as API parameters to the make-code endpoint, and keep credentials in environment variables or approved credential providers.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill advertises and instructs use of shell, network, file, and environment-backed operations but does not declare any permissions. This creates a transparency and governance gap: callers or policy engines may treat the skill as lower risk than it is, while it can still perform external requests, read/write local files, and invoke scripts.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 84% confidence
• Finding: The documented purpose is narrower than the actual behavior: the skill can also fetch package/version metadata, operate in direct mode without search, and synthesize/mock missing required parameters into generated requests. This mismatch can mislead users and reviewers about data flows and side effects, especially when mock parameter injection changes request content or when dependency lookup triggers extra network access.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The reference includes `setVerifyingSsl(false)` and `setDisableSSL(true)` as normal configuration examples without any warning, constraints, or indication that these options are only for controlled local testing. In an SDK integration guide, this can lead users to disable certificate validation or TLS entirely in production, enabling man-in-the-middle attacks, credential theft, and tampering with signed API traffic.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The documentation explicitly demonstrates setting `setSchema('http')` and `setVerifySsl(false)` without any warning or strong restriction to local testing. In an SDK integration guide, this can lead users to disable transport security in production, enabling man-in-the-middle attacks, credential theft, and tampering with API requests and responses.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The reference shows `configuration.scheme = "http"` and `configuration.verify_ssl = False` as normal configuration examples without any warning or safe-use boundary. This can lead users to disable transport security in production, enabling man-in-the-middle attacks, credential interception, and tampering with API requests and responses.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.