Social Sentiment

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 5:35 PM UTC
• Version: 1.4.0

Overview

The skill does what it describes: it connects to Xpoz to collect public social-media posts for sentiment analysis, with ordinary privacy and dependency cautions.

Install this only if you are comfortable using Xpoz, authenticating through its setup flow, sending brand/search queries to that service, and storing exported social-media CSVs locally. For stricter environments, review or pin mcporter and treat downloaded datasets as sensitive business or compliance data.

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:8

Finding

Unpinned Third-Party Executable Dependency

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 8-16
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

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)"}],
    },

Technical Analysis

The Skill declares installation and execution of the third-party npm package mcporter without specifying an exact version, integrity hash, lockfile, or verified package source. Consequently, the code installed at deployment time can differ from the code originally reviewed.

This creates a supply-chain risk: if the npm package, a transitive dependency, or its publisher account is compromised, a malicious release could be selected during installation. Malicious package lifecycle scripts could potentially execute during installation, while malicious CLI logic could execute when the documented mcporter call commands are invoked.

The Skill also delegates OAuth authentication to the external xpoz-setup Skill. Because that Skill is not included in this project, its authentication behavior and handling of credentials could not be verified in this audit.

Attack Path

1. An attacker compromises the mcporter npm package, its publisher account, or a transitive dependency and publishes a malicious version.
2. The Skill installation process resolves the unpinned package name to the compromised release.
3. Malicious code executes through an npm lifecycle script or when the installed mcporter executable is invoked.
4. The code runs with the privileges of the user or Agent performing the installation.
5. Depending on the execution environment, the malicious pac ...[truncated 709 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin mcporter to an exact, audited version rather than resolving the latest compatible release.
2. Use a lockfile and verify the package tarball with a trusted integrity hash.
3. Document and verify the expected npm publisher, source repository, and release provenance.
4. Disable npm lifecycle scripts during installation where operationally feasible, then explicitly permit only reviewed installation steps.
5. Review and pin all transitive dependencies or use a trusted internal package mirror with admission controls.
6. Run the dependency with least privilege in a sandbox or container with restricted filesystem, environment-variable, credential, and network access.
7. Include xpoz-setup in the auditable project scope or reference a pinned, independently audited version of that Skill.
8. Add automated dependency scanning and provenance verification to detect compromised, deprecated, or unexpectedly changed releases.

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 (1)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill clearly performs networked collection of social-media data through an external service (mcp.xpoz.ai), requires OAuth-based credentials, and instructs users to export CSVs for local analysis, but the description does not prominently warn users about those data flows. This can lead users to unknowingly transmit search terms, retrieve large volumes of third-party content, and store exported datasets locally without understanding the privacy, compliance, or operational implications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.