Security audit

Creator Watch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Twitter/X creator watchlist and analysis helper, with expected scraping and database import behavior but some broad triggers users should notice.

Before installing, be aware that this skill is meant to scrape public Twitter/X creator content and store imported posts in a database. Use it only where you are comfortable with that collection workflow, rate limits, and any platform or local database policies that apply.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

High

Confidence: 98% confidence
Finding: Several triggers such as 'who should I follow' and 'analyze creator' are broad, conversational phrases that can overlap with normal assistant usage. This raises the risk of misrouting benign requests into a skill that performs collection, scraping, and persistence of social media data without the user realizing that operational actions may follow.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: Several triggers such as 'who should I follow' and 'analyze creator' are broad, conversational phrases that can overlap with normal assistant usage. This raises the risk of misrouting benign requests into a skill that performs collection, scraping, and persistence of social media data without the user realizing that operational actions may follow.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill description mentions management and analysis but does not prominently warn users that it may scrape Twitter/X content and import the results into a database. Without clear disclosure, users may invoke the skill expecting simple recommendations or analysis while unintentionally triggering data collection and storage behavior.