amazon-opportunity-discoverer

• Outcome: Pass
• Latest audit: Aug 7, 2026 · 3:35 AM UTC
• Version: 1.0.9

Overview

This skill is a disclosed ZooData-powered Amazon opportunity scanner, with notable but purpose-aligned API, credential, and local CLI behavior.

Before installing, understand that this skill uses your ZooData API key and can spend API credits during scans. Prefer ZOODATA_API_KEY over the persistent ~/.zoodata/config.json option, and confirm estimated credit cost before broad scans.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill explicitly describes access to environment variables, local files, network calls, and shell execution, but does not declare matching permissions. This creates a trust and sandboxing gap: users and hosting systems may underestimate the skill's ability to read credentials, invoke commands, and reach external services, increasing the chance of unintended secret exposure or over-privileged execution.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 89% confidence
• Finding: The skill is presented as a narrowly scoped opportunity scanner, but the documented behavior exposes a much broader general-purpose Amazon research CLI with additional workflows and endpoints. Scope mismatch is dangerous because policy routing, user consent, and review decisions may approve the skill for low-risk use while it can actually perform materially different operations, including raw review retrieval and broader market intelligence functions.

Vague Triggers

Medium

• Confidence: 78% confidence
• Finding: The invocation phrases are broad enough to match common shopping or business questions, which can cause the skill to activate outside its intended context. In an over-privileged skill, misrouting matters because it may trigger external API usage, shell-backed tooling, or credit consumption on user prompts that did not clearly request this workflow.

Session Persistence

Medium

• Category: Rogue Agent

Content

print("    export ZOODATA_API_KEY='hms_live_yourkey'", file=sys.stderr)
    print("", file=sys.stderr)
    print("  Method 2: User-home config (persistent, shared across all skills)", file=sys.stderr)
    print("    mkdir -p ~/.zoodata && chmod 700 ~/.zoodata", file=sys.stderr)
    print('    (umask 077; echo \'{"api_key":"hms_live_yourkey"}\' > ~/.zoodata/config.json)', file=sys.stderr)
    print("    # keep the file private (0600) — it holds a bearer credential", file=sys.stderr)
    print("", file=sys.stderr)

• Confidence: 78% confidence
• Finding: The CLI supports persistent storage of a bearer API key in ~/.zoodata/config.json, creating a long-lived credential on disk that can be reused across skills and sessions. In a multi-skill or shared-host context, persistent secrets increase the blast radius of local compromise and make accidental exposure more likely than ephemeral environment-based credentials.

VirusTotal

55/55 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.