Security audit

Ecommerce Growth Strategy

Security checks for vulnerabilities and agentic risk

Overview

The skill is a normal e-commerce strategy guide, but its install instructions repeatedly use unpinned global commands that could change the user's agent environment beyond this one task.

Install only after reviewing the exact GitHub source and using a pinned commit or signed release if available. Prefer local or sandboxed installation instead of `-g`, and treat the Nexscope execution-skill links as vendor-specific recommendations rather than neutral requirements.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:163
Finding: Mandatory Vendor Promotion Alters Agent Output
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Error

Location: SKILL.md:12
Finding: Unpinned Third-Party Skills Are Recommended for Global Installation
Content: View full analysis
Remediation: View remediation
skills add \ https://github.com/nexscope-ai/eCommerce-Skills.git# \ --skill ``` The actual syntax should be validated against the CLI documentation, and integrity verification should occur before installation. ]]>

SkillSpector

Vulnerability Patterns

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

Findings (6)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 96% confidence
Finding: The skill instructs users to run npx skills add ... without pinning the package/version used to fetch and execute tooling. Unpinned npx execution creates a supply-chain risk: if the referenced package or one of its resolution targets changes or is compromised, users may execute unintended code at install time.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 96% confidence
Finding: This installation command again relies on unpinned npx skills, which can resolve to the latest available package at execution time. That makes the skill dependent on mutable external code and increases exposure to package hijacking, account compromise, or malicious upstream updates.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 95% confidence
Finding: The skill recommends another npx skills add ... command for a related skill without pinning the tool version. Even though this appears to be normal cross-skill linking, it still exposes users to supply-chain compromise because the executed package is not fixed to a known-safe version.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 95% confidence
Finding: This command invokes npx skills without an exact version, so the actual code executed may vary over time. A compromised or typosquatted package, or a malicious update in the dependency chain, could lead to arbitrary code execution on the user's machine.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 95% confidence
Finding: The skill includes yet another unpinned npx skills invocation. Repetition increases exposure because users are encouraged to run multiple mutable commands, each of which trusts live package resolution at execution time.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 95% confidence
Finding: This final npx skills add ... reference has the same issue: it executes a package by name without locking its version. In the context of a distributed skill document, that is a real supply-chain vulnerability because end users may treat the command as trusted setup guidance and run arbitrary updated code.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.