Tweet Writer
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent instruction-only tweet-writing skill with no code, credentials, posting access, or persistence; the main thing to notice is its disclosed use of web research.
This skill appears safe to use for ordinary tweet and thread drafting. Be careful not to include confidential strategy, client, or product information in prompts if you do not want those details used in web searches.
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 a prompt includes confidential client names, campaign plans, or unreleased product details, those terms could be sent through web search.
The skill explicitly instructs the agent to use an external search tool as part of drafting. This is disclosed and aligned with the purpose, but user-provided niche/topic details may be included in search queries.
Before writing ANY tweet, you MUST research viral examples... Use WebSearch to find:
Avoid including sensitive or confidential details in the research query, or do not invoke this skill for confidential drafting.
Users have less information about who maintains the skill or where to review its original source.
The skill has limited provenance information. Because the supplied artifacts are instruction-only with no code or install steps, this is a transparency note rather than a security concern.
Source: unknown; Homepage: none
Review the visible SKILL.md instructions before enabling it, and prefer known-source skills for workflows that require credentials, posting access, or code execution.