Security audit

X Twitter Post Publisher

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly for posting to X/Twitter, but it can publish publicly from a logged-in account without requiring a final user confirmation.

Review each post manually before using this skill. Treat it as capable of publishing from the currently logged-in X/Twitter account, and prefer a dry run or explicit confirmation step showing the final post text and target account before any live post.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

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

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill automates a live, externally visible posting action on X/Twitter and provides direct commands to publish, but it does not require an explicit user confirmation step immediately before the irreversible action. In an agent setting, this increases the risk of accidental or unintended posting from a logged-in account, which can cause reputational harm, disclosure of sensitive content, or unauthorized publication.

Static analysis

No suspicious patterns detected.