amazon-sorftime-research-market-skill

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:28 PM UTC
• Version:
  1.0.0

Overview

This is a coherent Sorftime-backed Amazon product research skill, with the main caution being careful handling of the Sorftime API key and saved raw research data.

Install only if you trust Sorftime with the product keywords, ASINs, and research parameters you submit. Keep the Sorftime API key out of screenshots, logs, shell history, and shared reports, and review or delete the generated raw/ files after use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill states that the API key is automatically read from `.mcp.json` but does not warn users that this file contains sensitive credentials or describe safe handling boundaries. In an agent setting, undocumented secret access increases the risk of accidental exposure in logs, prompts, reports, debugging output, or downstream tool calls.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill says all raw API responses are saved under `raw/` without warning that those responses may contain account-linked, proprietary, or otherwise sensitive data. Persisting unreviewed raw responses expands the data exposure surface and may leave sensitive information in local artifacts that are later shared or ingested by other tools.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The documentation shows API credentials passed in the URL query string (`?key={API_KEY}`), which is commonly exposed through shell history, logs, proxies, browser tooling, and monitoring systems. Even though this is only a reference document, it normalizes an insecure authentication pattern and gives no warning about credential leakage risks.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The documentation places the API key directly in the request URL, which can leak secrets through shell history, proxy logs, browser history, monitoring systems, and server access logs. In an agent skill context where users may copy-paste examples verbatim, this increases the chance of credential exposure and unintended reuse of privileged keys.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The documentation instructs users to place the API key in the URL query string (`?key={API_KEY}`), which is commonly exposed through browser history, proxy/server logs, analytics tooling, shell history, and monitoring systems. Even though this is documentation rather than executable code, it normalizes an unsafe credential-handling pattern that can lead to accidental secret disclosure when users copy the example into real environments.

VirusTotal

66/66 vendors flagged this skill as clean.