Back to skill

Security audit

amazon-review-insights

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports Amazon review analysis, with disclosed API authentication, browser-extension requirements, and point-consuming operations.

Use a read-only API key if you only need existing results. Confirm point spending before analysis; direct script calls do not ask again. For collection, review the extension's permissions and use an isolated browser profile with a dedicated buyer account. Prefer environment-based key configuration and a current, pinned Requests release. The external extension itself was not included in the inspected package.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/api_client.py
Finding

Points-consuming operations lack an executable approval gate

Content
View full analysis

Impact

Direct invocation can consume the user's account points without recording or checking the required approval. This is a missing authorization safeguard, not evidence of credential theft or intentional unauthorized charging.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (8)

Tainted flow: 'headers' from os.environ.get (line 68, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/api_client.py (reported line 75)May include surrounding context.

python
}

        try:
            response = requests.post(url, json=data or {}, headers=headers, timeout=30)
            response.raise_for_status()
            result = response.json()
            if result.get("code") != 0:

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
78% confidence
Finding

The only visible operation requests a device check rather than an Amazon review intelligence function. The API client implementation is not supplied, so its precise behavior cannot be verified. If this action is merely a supporting authentication or licensing check, it would not constitute a mismatch; however, that relationship is not established by the provided code.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill forces English responses for users writing in any language other than Chinese, without user opt-in.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The language instruction requires English even when the user writes in another non-Chinese language, such as Spanish or Japanese. Calling English the 'unified language' does not provide a domain-specific justification or offer users a language choice.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/api_reference.md (reported line 1204)May include surrounding context.

python
import requests

resp = requests.post(url, headers=headers, json=payload)
if resp.status_code == 400:
    err = resp.json().get("detail", {})
    msg = err.get("msg", "")

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/api_client.py (reported line 75)May include surrounding context.

python
}

        try:
            response = requests.post(url, json=data or {}, headers=headers, timeout=30)
            response.raise_for_status()
            result = response.json()
            if result.get("code") != 0:

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The open-ended requirement permits different dependency versions across installations, including older releases with known vulnerabilities and future releases that have not been reviewed. This is a dependency-management weakness rather than evidence of an exploitable installation; the skill's network-fetching purpose makes Requests security relevant, but no runtime usage is provided.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
requests>=2.28.0

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
40% confidence
Finding

OSV returned advisories for this package, but its resolved version is unknown. A package-name lookup does not establish whether the installed release is affected by those advisories.

Content

No source excerpt is available for this finding.