Security audit

Amazon Brand Shield

Security checks for vulnerabilities and agentic risk

Overview

The skill's local brand-protection scripts are purpose-aligned, but the documented installer uses an unpinned global npx install from mutable remote sources.

Review the skill contents before installing, prefer a pinned package version and immutable repository commit or checksum, and avoid the global `-g` install unless you want this skill available across future sessions. The runtime scripts appear offline and low-privilege, but the install command relies on mutable upstream sources.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:13
Finding: Unpinned Third-Party Installer Executes Mutable Remote Content with Global Scope
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 92% confidence
Finding: The installation command uses npx skills without pinning a specific package version, which means users may execute whatever version is currently resolved from the registry at install time. This creates a supply-chain risk: a compromised upstream package, dependency, or newly published breaking/malicious version could run code on the user's system during installation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This file contains user-facing reporting in two languages, but the implementation hard-codes English as default and Chinese only when a specific flag is supplied. Because the skill enforces a locale choice in code rather than detecting or asking for user preference, it creates a language/locale policy concern if the user's preferred language is different.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This code includes a language-specific output mode selected by a --zh flag and ships separate Chinese templates, but the file does not document any locale justification or broader language-choice policy beyond English vs. Chinese. Under the policy rule, forcing or embedding a specific locale without explicit opt-in context or justification can be a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.