x-agent
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent and guardrailed, but users should understand it can guide X account posting automation and requires locally managed API credentials.
Before installing, decide whether you want only monitoring, draft approval, or automation. Do not paste API keys into chat, use a dedicated low-privilege X app/account if possible, set hard posting and reply limits, and require manual approval until you are comfortable with the workflow.
Findings (2)
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.
If enabled, the agent could help publish or reply from an X account, which can affect public reputation.
The skill may guide posting and replying automation on a public X account, which is a sensitive external action, but the artifact makes automation opt-in and requires guardrails.
Phase 3 — Limited automation (default OFF) Enable only after user confirmation. Automation constraints: 1. Allowed actions only from pre-approved playbooks. 2. Hard caps: - max posts/day - max replies/hour
Start in monitor-only or draft-and-approve mode, set concrete post/reply limits, and keep explicit human approval for publishing unless you fully trust the playbook.
Credentials could grant access to post or manage activity on the connected X account depending on their scopes.
The skill expects X API credentials for account workflows; this is purpose-aligned and includes a safe handling instruction, but credentials are not declared in the registry metadata.
Configure API credentials in local environment (never in chat).
Use least-privilege X API credentials, keep them out of chat, store them only in a local secrets mechanism, and revoke them if automation is no longer needed.