Lead Generation

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 5:38 PM UTC
• Version: 2.2.0

Overview

This skill is a coherent lead-generation workflow that uses disclosed Xpoz network access, OAuth setup, and local files for reusable research and deduplication.

Install only if you trust Xpoz, the mcporter npm package, and the xpoz-setup skill. Expect product research, search queries, and lead history to persist locally under data/lead-generation, and delete or secure those files if they contain sensitive sales or customer-discovery information.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:9

Finding

Unpinned External Dependencies Create a Mutable Supply-Chain Execution Path

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 9-15 and line 47
Vulnerability Type: Unpinned npm package and externally delegated setup skill
Risk Level: Medium

Vulnerable Code

yaml

"requires": {
  "bins": ["mcporter"],
  "skills": ["xpoz-setup"],
  "network": ["mcp.xpoz.ai"],
  "credentials": "Xpoz account (free tier) — auth via xpoz-setup skill (OAuth 2.1)"
},
"install": [{"id": "node", "kind": "node", "package": "mcporter", "bins": ["mcporter"], "label": "Install mcporter (npm)"}],

markdown

Run `xpoz-setup` skill. Verify: `mcporter call xpoz.checkAccessKeyStatus`

Technical Analysis

The skill declares installation of the mcporter npm package without an exact version or integrity hash. Consequently, the installed code can change after this skill has been reviewed. The skill also delegates authentication to the external xpoz-setup skill without identifying a pinned version, immutable source, or reviewed implementation.

Package installation and OAuth setup are security-sensitive operations. An npm package can execute installation lifecycle scripts, while an authentication helper may access tokens, browser authorization sessions, configuration files, or environment variables. If either mutable dependency is compromised, substituted, or resolved from an unsafe source, attacker-controlled code could execute with the permissions of the process installing or invoking the skill.

The audited file does not establish that either current dependency is malicious. The vulnerability is the absence of controls ensuring that the reviewed dependency is the same dependency executed later.

Attack Path

1. An attacker compromises the npm package, its maintainer account, the package distribution channel, or the externally resolved xpoz-setup skill.
2. A malicious release or substituted implementation is published under the dependency identifier expected by this skill.
3. Th ...[truncated 1006 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin mcporter to an exact reviewed version rather than resolving the latest compatible package.
2. Record and verify the package integrity hash through a committed lockfile or equivalent integrity mechanism.
3. Restrict package resolution to a trusted registry and use lockfile-enforced, reproducible installation.
4. Disable npm lifecycle scripts where they are unnecessary; otherwise, review all lifecycle scripts before installation.
5. Pin xpoz-setup to an immutable version or content digest and document its trusted source.
6. Audit the setup skill for credential handling, OAuth scopes, filesystem access, subprocess execution, and outbound connections.
7. Request only the minimum OAuth scopes required for lead discovery and store tokens in an operating-system credential store rather than plaintext files.
8. Run dependency installation and authentication in a sandbox with restricted filesystem access, least-privilege credentials, and an outbound network allowlist.
9. Add automated dependency provenance, signature, vulnerability, and integrity verification to the release process.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The skill explicitly instructs saving researched product data and generated queries to local files, but it does not warn the user that potentially sensitive business information will persist on disk. In a lead-generation context, this can expose proprietary product strategy, targeting assumptions, or customer research to other local users, backups, or later unintended reuse.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill stores lead history in a local deduplication file without warning that usernames, post identifiers, and interaction history will persist across runs. Because this data may contain personal data or sales-intelligence records, undisclosed local retention can create privacy, compliance, and unintended data exposure risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.