Back to skill
Skillv3.8.5

ClawScan security

twitterapi-io · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 29, 2026, 4:06 AM
Verdict
suspicious
Confidence
high
Model
gpt-5-mini
Summary
The skill largely matches its stated purpose (using TwitterAPI.io) but has clear documentation/metadata mismatches around credentials and sensitive inputs (API key, login cookies, proxy credentials) that are not declared in the registry, so you should not install without clarifying those gaps.
Guidance
This skill appears to implement what it claims (TwitterAPI.io endpoints) but the package metadata fails to declare the sensitive inputs it actually needs. Before installing: 1) confirm the registry/provider will require you to supply TWITTERAPI_IO_KEY (X-API-Key) and that this will be stored/used securely; 2) understand that write operations need login_cookies (session cookie from login) and a residential proxy (credentials), both of which are highly sensitive — do not paste them into public chats or unsecured logs; 3) be cautious calling endpoints that send login_cookies in GET query params (they can end up in logs/urls); 4) verify the skill author/source and prefer official Twitter/X APIs if you need long-running write access; and 5) ask the publisher to update the skill metadata to list required env vars/primary credential and to document how secrets are expected to be provided so you can make an informed decision.

Review Dimensions

Purpose & Capability
concernThe skill's name/description (TwitterAPI.io integration) matches the SKILL.md content, but the registry metadata declares no required environment variables or primary credential while the SKILL.md repeatedly requires an X-API-Key ($TWITTERAPI_IO_KEY) and, for write actions, 'login_cookies' plus residential proxy credentials. That omission is an incoherence: a Twitter API skill should declare the API key and note additional sensitive inputs.
Instruction Scope
noteSKILL.md provides detailed curl examples and explicit instructions for read/write/login flows and warns about sending login_cookies in GET query params. It does not instruct the agent to read arbitrary host files, but it tells users to store the API key in a .env and to supply login_cookies and proxy credentials (sensitive). The guidance to avoid plain shell export is helpful, but the document exposes workflows that could leak secrets (login_cookies in URLs) and relies on the user to handle secrets correctly.
Install Mechanism
okInstruction-only skill with no install spec and no code files — low risk from installation artifact perspective (nothing is downloaded or executed on disk).
Credentials
concernThe skill requires at minimum TWITTERAPI_IO_KEY (X-API-Key) and—if performing writes—login_cookies and residential proxy credentials (including user:pass). None of these are declared in the registry metadata or listed as a primary credential. Requiring login cookies and proxy credentials is expected for this provider but is sensitive; the registry should declare these env/config requirements and the primary credential.
Persistence & Privilege
okThe skill does not request persistent 'always' inclusion and has no install-time actions that modify other skills or system settings. Autonomous invocation is allowed (platform default) but nothing else elevates privilege.