ClawHub
Back to skill

Security audit

opentwitter

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Twitter/X lookup skill that sends user-directed API requests and a required token to a disclosed 6551 endpoint.

Install only if you trust the 6551 API service with your TWITTER_TOKEN and the usernames, searches, follower-event checks, or deleted-tweet lookups you submit. Prefer a dedicated or revocable token, avoid sensitive investigations unless appropriate, and review the provider's privacy and retention practices.

SkillSpector

By NVIDIA
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 (7)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill repeatedly instructs users to send a Bearer token to a third-party service but does not include any warning about credential sensitivity, storage, rotation, scope, or trust of the remote endpoint. This is dangerous because users may paste production secrets into an unvetted external API workflow without understanding that the token will be transmitted off-host on every request.

External Transmission

Medium
Category
Data Exfiltration
Content
env:
        - TWITTER_TOKEN
      bins:
        - curl
    primaryEnv: TWITTER_TOKEN
    emoji: "\U0001F426"
    install:
Confidence
87% confidence
Finding
The skill metadata declares curl and a primary secret environment variable, indicating the skill is designed to transmit credentials and user query data to an external network service. In this context, the behavior is expected functionality, but it is still a real security concern because it creates an external data egress path and relies on trust in a third-party API.

External Transmission

Medium
Category
Data Exfiltration
Content
Search tweets with various filters.

```bash
curl -s -X POST "https://ai.6551.io/open/twitter_search" \
  -H "Authorization: Bearer $TWITTER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"keywords": "bitcoin", "maxResults": 20, "product": "Top"}'
Confidence
92% confidence
Finding
This example sends search parameters plus the Bearer token to https://ai.6551.io, creating an explicit outbound data flow to a third-party service. While this matches the skill's stated purpose, it remains security-relevant because both credentials and potentially sensitive search terms leave the local environment.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Get new followers
curl -s -X POST "https://ai.6551.io/open/twitter_follower_events" \
  -H "Authorization: Bearer $TWITTER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"username": "elonmusk", "isFollow": true, "maxResults": 20}'
Confidence
91% confidence
Finding
This request sends the token and a target username to an external API to retrieve follower/unfollower events. The danger is not hidden code execution, but undisclosed data egress and credential use against a remote service, which can expose account-related intelligence and secrets if users do not understand the trust boundary.

External Transmission

Medium
Category
Data Exfiltration
Content
Get deleted tweets from a user.

```bash
curl -s -X POST "https://ai.6551.io/open/twitter_deleted_tweets" \
  -H "Authorization: Bearer $TWITTER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"username": "elonmusk", "maxResults": 20}'
Confidence
92% confidence
Finding
This example transmits a Bearer token to a third-party endpoint to retrieve deleted tweets, which may involve sensitive or controversial data handling. The skill provides no warning about credential transmission, data retention, or the sensitivity of the content being queried, increasing the risk of uninformed use.

External Transmission

Medium
Category
Data Exfiltration
Content
Get which KOLs (Key Opinion Leaders) are following a user.

```bash
curl -s -X POST "https://ai.6551.io/open/twitter_kol_followers" \
  -H "Authorization: Bearer $TWITTER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"username": "elonmusk"}'
Confidence
90% confidence
Finding
This call sends a username and Bearer token to an external service to determine KOL follower relationships. Although this is ordinary API usage for the skill, it is security-relevant because it creates outbound transmission of secrets and user-requested intelligence to a third-party operator without explicit risk disclosure.

External Transmission

Medium
Category
Data Exfiltration
Content
### Crypto Twitter KOL Tweets
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_user_tweets" \
  -H "Authorization: Bearer $TWITTER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"username": "VitalikButerin", "maxResults": 10}'
Confidence
90% confidence
Finding
This workflow example transmits the Bearer token and request parameters to a third-party API. In context this is intended functionality, but it is still a valid finding because the documentation normalizes credentialed outbound requests without any prominent warning about secret handling or external disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.