Security audit

Auto Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malware, but it is misleading because it presents real multi-platform publishing and tracking while the code fabricates publish URLs and analytics results.

Install only if you treat this as a demo or scaffold. Do not rely on its publish success URLs or analytics as real, and do not put real platform credentials in scripts/config.json unless you first review and harden the code, add real API integrations, use safer secret storage, and add explicit confirmation before any live or batch posting.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The file advertises itself as a multi-platform auto publisher, but each platform-specific publish method only logs inputs, sleeps, and returns a fabricated success URL derived from the current timestamp. This creates a deceptive success condition that can mislead users or downstream automation into believing content was actually published, causing integrity and operational failures.

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The module-level documentation presents the script as a real post-publication tracker, but every platform implementation is explicitly marked as simulated and returns fabricated metrics. This can mislead users or downstream automation into treating fake analytics as real business data, enabling bad decisions, false reporting, or deceptive workflows.

Intent-Code Divergence

Medium

Confidence: 93% confidence
Finding: The DataTracker.track method claims to track video data and return tracking results, but it only delegates to mock backends that synthesize numbers. In a skill context, that discrepancy is dangerous because other components may trust the returned values as authoritative and use them in reports, billing, ranking, or performance analysis.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The README promotes automatic multi-platform publishing and metadata submission to third-party services without clearly warning users that invoking the skill can post content externally and transmit associated titles, descriptions, tags, and account-linked data. In a publishing automation context, this omission increases the risk of unintended posts, privacy leakage, and reputational or account impact if users do not fully understand the scope of the action.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The credential setup instructions tell users to place platform API secrets in a local JSON file but do not warn about the sensitivity of those credentials or recommend safer storage practices. If that file is committed to source control, shared, or left with weak filesystem permissions, attackers could obtain API keys and secrets that enable unauthorized posting, account abuse, or access to platform data.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The batch publishing documentation describes bulk posting across platforms without warning that one command may trigger multiple irreversible external actions from connected accounts. In this skill's context, that can magnify mistakes, causing accidental mass publication, metadata leakage, or widespread brand/account damage across several services at once.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly promotes automatic publishing and post-publication tracking across multiple third-party platforms, but it does not warn users that their videos, titles, descriptions, tags, account-linked metadata, and analytics will be transmitted to external services. This creates a meaningful privacy and consent risk, especially because users may not realize the scope of data sharing or that platform APIs may retain or further process uploaded content and engagement data.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The documentation instructs users to store API secrets and tokens directly in a local JSON file without any guidance on file permissions, secret management, exclusion from version control, or encryption. This increases the chance of credential leakage through source control commits, local compromise, backups, logs, or accidental sharing, which could enable unauthorized publishing or access to connected platform accounts.

Static analysis

No suspicious patterns detected.