ClawHub
Back to skill

Security audit

Amazon Sp Api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Amazon Seller Central API helper that uses the expected credentials and network calls for its stated purpose.

Install only if you intend to let the agent access your Amazon Seller Central data through SP-API. Use least-privilege Amazon/IAM credentials, keep secrets out of chat, and write reports only to deliberate, non-sensitive paths.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill clearly uses sensitive capabilities: it reads multiple credential-bearing environment variables, makes outbound network requests to Amazon SP-API, and writes files via report output options, yet the metadata declares only runtime requirements and no explicit permissions model. This creates a transparency and policy gap: an agent or platform may grant or execute the skill without users understanding that secrets will be consumed and data may be written or exfiltrated over the network.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The `--output` argument is passed directly to `open(output, "w")` with no path restriction, validation, or warning, allowing the caller to overwrite any file writable by the current user. In an agent-tool context, this is risky because an LLM or upstream workflow could be induced to save untrusted report contents to sensitive locations such as shell startup files, config files, or other application data.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
# ── Env helpers ──────────────────────────────────────────────────────────

def _env(key: str, fallback: str = "") -> str:
    return os.environ.get(key, fallback)


def _require_env(*keys: str) -> dict[str, str]:
Confidence
70% confidence
Finding
Code accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.

Static analysis

No suspicious patterns detected.