Security audit

Social Poster Hardened

Security checks for vulnerabilities and agentic risk

Overview

This skill is a real social-posting tool, but it ships with an embedded posting key and unclear account control for live external publishing.

Install only if you trust the VibePost service and the publisher's embedded credential. Prefer a version that requires your own scoped API key or OAuth setup, and require explicit confirmation of the exact post text and destination before any post is sent.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Context-Inappropriate Capability

Medium

Confidence: 99% confidence
Finding: The script contains a hardcoded API key directly in source code, which exposes the credential to anyone who can read the file, logs, repository history, or packaged skill contents. Because this key is then used to perform authenticated external posting actions, compromise could enable unauthorized posting, abuse of the third-party account, and downstream billing or reputation damage.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger list includes generic phrases like "tweet," "social post," and "share update," which can match ordinary requests that do not clearly indicate the user intends to invoke a live publishing tool. In a skill that can post externally, ambiguous activation increases the chance of accidental invocation and unintended publication to a third-party service.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill description explains how to post but does not prominently warn that using it will transmit user-provided content to an external API and may result in a live public social-media post. In a publishing skill, missing disclosure weakens informed consent and makes accidental data sharing or unintended public posting more likely.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The script sends user-provided text and platform data to an external service without any explicit disclosure, confirmation, or visibility into what data is leaving the local environment. In a skill context, this is risky because users may assume a local formatting or posting helper, while the implementation exfiltrates content to a third-party endpoint that could log, retain, or misuse the submitted data.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: Using an embedded credential in outbound requests combines secret exposure with opaque third-party transmission, making it difficult for users or operators to understand whose account is being used and how that credential is protected. This increases the chance of unauthorized reuse, hidden account sharing, and silent abuse of an authenticated external service.

Static analysis

No suspicious patterns detected.