ClawHub
Back to skill

Security audit

Tweet Processor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small tweet-to-notes helper that discloses its local note-file writes and shows no hidden, destructive, or deceptive behavior.

Install this only if you want tweet links to be processed into local tweet-notes files. Review the generated note content before relying on it, because it comes from external tweets, and avoid sending tweet links casually if you do not want the skill to append notes automatically.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README states that the agent will 'update the files' and 'report what was added,' but it does not clearly warn users up front that activating the skill causes automatic persistent modification of local note files. This can lead to unintended writes, user surprise, and poisoning of the note corpus with untrusted web-derived content, especially because the trigger is as simple as sending a tweet URL.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill says 'When user sends a tweet URL, automatically' but does not clearly scope when the action should trigger or require confirmation before browsing and writing to local files. That ambiguity can cause unintended activation on ordinary mentions of tweet links and lead to unreviewed ingestion of untrusted content into the user's workspace.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is designed to append content into local note files automatically, but the description does not prominently warn the user that external tweet content will be persisted to disk. This creates a risk of silent file modification, note poisoning, and accidental inclusion of malicious or low-integrity content from tweets into trusted local knowledge files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.