ClawHub
Back to skill

Security audit

FX Twitter Translate

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it fetches public Twitter/X tweet text through fxtwitter and translates it into Chinese, with no local code, persistence, or credential access.

Install this if you are comfortable with tweet URLs and fetched public tweet text being requested through the public fxtwitter service. Avoid using it for private, sensitive, or access-controlled content; this skill is best suited to translating public tweets only.

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The metadata states the skill translates content to Chinese by default, without indicating that this is contingent on user request or configurable preference. While not a classic security flaw, it can cause unintended data transformation or user-surprising behavior, especially if the skill auto-triggers on matching links.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to send tweet-derived data to a third-party public API but does not warn the user that their provided link and requested content will be transmitted off-platform. This creates a privacy and transparency issue because users may reasonably expect translation to occur locally or through trusted first-party infrastructure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This section documents transforming user-provided Twitter/X links into requests to api.fxtwitter.com, which is an external third-party service. The risk is not remote code execution, but external transmission of user-supplied URLs and requested content to a public API without any trust boundary explanation, validation guidance, or user consent.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

  • https://x.com/:username/status/:tweetId → extract tweetId
    • https://twitter.com/:username/status/:tweetId → extract tweetId
    • https://fxtwitter.com/:username/status/:tweetId → extract tweetId
    • https://api.fxtwitter.com/:username/status/:tweetId → already API format
  1. Convert to fxtwitter API URL:
    text

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The skill instructs a direct GET request to a public third-party API, creating a clear external data flow. In context this is expected functionality, but it remains a genuine security/privacy concern because the skill does not describe safeguards, user notice, authentication expectations, or how malicious or malformed responses are handled.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

  1. Convert to fxtwitter API URL:

    text
    https://api.fxtwitter.com/:username/status/:tweetId

  2. GET request to fetch JSON

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow mandates Simplified Chinese output regardless of user preference and does not document an opt-in or justified restriction. In an auto-triggered skill, this can lead to unexpected handling of user content and weakens informed consent around how the content will be processed and presented.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The example operationalizes the external transmission by showing a real request to api.fxtwitter.com, reinforcing that the skill sends user-referenced content to a third party. The context makes the transmission intentional rather than covert, but it is still a real privacy and trust-boundary issue because no explicit user warning or approval is built into the workflow.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
Flow:
- Extract username `invideoOfficial`, tweetId `2033866107166318666`
- API request to `https://api.fxtwitter.com/invideoOfficial/status/2033866107166318666`
- Extract full article text
- Translate to Chinese markdown
- Output with author credit and original link

Static analysis

No suspicious patterns detected.