fapi.uk Twitter All-in-One API

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  1.0.0

Overview

The skill is a coherent Twitter/X automation helper, but it asks for powerful account credentials and enables account-changing actions without clear confirmation controls.

Review carefully before installing. Use a low-risk or dedicated Twitter/X account, do not paste real tokens into chat, store credentials only through a secure config/secret mechanism, and require explicit confirmation before any post, reply, follow, unfollow, block, unlock, or paid credit-consuming action.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The skill is described as acting on broad natural-language requests with no clear trigger boundaries, exclusions, or confirmation requirements. In a skill that can post tweets, follow/unfollow, block, and interact with authenticated accounts, ambiguous activation increases the risk of unintended account-affecting actions from casual or misinterpreted prompts.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README advertises write-capable actions such as posting, retweeting, following, blocking, and DM-related uploads without clearly warning that these can change a user's account state and may be hard or impossible to fully undo. In the context of authenticated Twitter account access, missing warnings and confirmation expectations materially raise the chance of harmful or accidental actions.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: The README explicitly tells users they can paste their apiKey and auth_token directly into chat, creating a direct natural-language path for exposing secrets in a conversational channel. Chat transcripts may be logged, retained, shared, or surfaced to other components, making credential compromise and account takeover significantly more likely.

Missing User Warnings

High

• Confidence: 98% confidence
• Finding: The skill explicitly instructs users to paste sensitive credentials such as apiKey and auth_token directly into chat. Secrets shared in conversational channels may be logged, retained, exposed to other tools/components, or accidentally disclosed in future context, creating a real credential-handling vulnerability.

Ssd 3

High

• Confidence: 99% confidence
• Finding: The skill documentation encourages collection of API credentials through natural-language chat, which is a classic sensitive-data exposure pattern. Because the same skill performs authenticated Twitter operations, leaked tokens could be used to impersonate the user, post content, access protected operations, or abuse paid API balances.

Ssd 3

High

• Confidence: 99% confidence
• Finding: The skill creates a natural-language workflow for exposing API credentials in chat, including high-value authentication material like auth_token. In an agent setting, this is especially dangerous because chat content may be persisted, reused as context, surfaced to plugins, or visible to operators, making credential compromise and account abuse plausible.

VirusTotal

66/66 vendors flagged this skill as clean.