X Founder Operations
SuspiciousAudited by ClawScan on May 10, 2026.
Overview
The skill is coherent for X account operations, but it encourages public posting, replies, DM handling, recurring automation, and logging without clearly requiring user approval, credential scope, or retention limits.
Use this skill cautiously for drafting, planning, and analytics. Before giving it any X account access, require explicit approval for every post, reply, quote tweet, or DM; avoid DM access unless necessary; and decide where reports/logs will be stored and how to delete them.
Findings (5)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent could publish or interact from the user's X account in ways that affect reputation, business relationships, or public messaging.
The skill can be invoked automatically and gives instructions for public account actions, but the provided text does not add an explicit approval gate before posting, replying, or engaging from the user's account.
auto_invoke: true ... **Post** 2-3 tweets ... reply to every comment in the first hour ... **Engage** with core circle
Default to draft-only mode and require explicit user approval before posting tweets, replies, quote tweets, or DMs.
Private messages and account activity may be exposed to the agent without a clear permission contract or scope boundary.
Reading mentions, replies, and especially DMs requires delegated access to the user's X account, but the metadata declares no primary credential or scoped permission requirement.
Check overnight mentions, replies, and DMs
Declare the required X authentication method and scopes, avoid DM access by default, and let users explicitly opt in to any private-message or account-mutation permissions.
Private or business-sensitive X activity could be stored in reports or logs longer than expected and reused in future planning.
The skill also describes scanning DMs, mentions, posts, and account metrics; unbounded logging could persist sensitive social/account data without stating storage location, retention, redaction, or deletion controls.
Log everything — All task executions and their outcomes should be traceable
Document exactly what is logged, where it is stored, how long it is retained, and provide redaction and deletion guidance, especially for DMs.
If implemented as written, account monitoring and recommendations could continue on a schedule rather than only when the user asks.
The reference material describes recurring automation and missed-job recovery, although the provided artifacts do not show an installer that actually creates cron jobs.
Automated task schedule for daily X operations ... If Cron Job Missed ... Run the missed task as soon as possible
Keep scheduled workflows as reminders unless the user explicitly enables automation, and provide a clear stop/disable procedure.
Users have less ability to verify authorship or inspect the upstream project before trusting it with account-operations guidance.
The skill has helper scripts listed, but the registry metadata does not provide an external source or homepage for provenance review.
Source: unknown; Homepage: none
Provide a public source repository or homepage, and review the included scripts before enabling account access.