Api Push Product Platform

• Outcome: Review
• Latest audit: Jun 17, 2026 · 10:51 PM UTC
• Version: 1.0.0

Overview

The skill is purpose-built to push API documentation to a product platform, but it sends local API-definition data to a plain-HTTP external endpoint and encourages automation without enough review controls.

Install only if this endpoint is your approved product-platform destination and the API definitions are safe to share there. Prefer reviewing and sanitizing generated API JSON before pushing, avoid the pre-push automation example unless your team has approved it, and use an HTTPS/authenticated endpoint if available.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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: 90% confidence
• Finding: The skill clearly instructs reading local files and sending their contents over the network, but it declares no permissions. This creates a transparency and governance gap: users and platforms cannot accurately assess that local API definitions and related data may be exfiltrated to an external service.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The natural-language trigger is phrased broadly enough that ordinary requests about API docs or synchronization could invoke a workflow that prepares and transmits data externally. Over-broad activation increases the chance of unintended execution and accidental disclosure of internal API definitions.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill documents an external HTTP endpoint and a workflow for transmitting backend API definitions, but it does not prominently warn users that potentially sensitive internal interface data will be sent outside the local environment. Because the endpoint uses plain HTTP rather than HTTPS, the confidentiality risk is higher due to possible interception or tampering in transit.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation instructs users to automatically extract and push API definitions from source code to a remote HTTP endpoint during CI/CD and pre-push operations, but it provides no consent prompt, scope restriction, or warning that internal project metadata will be transmitted off-repository. This creates a real risk of unreviewed exfiltration of sensitive architecture details, internal endpoints, and parameter schemas, especially because the examples encourage automation at commit/push time.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The script sends potentially sensitive API definition content to a remote endpoint over plain HTTP, which provides no transport encryption or server authenticity. This enables interception or modification of the transmitted data by any party on the network path, and the script also lacks any explicit warning or confirmation before exfiltrating the content to an external system.

VirusTotal

63/63 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.