Tweet Ideas Generator

PassAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill coherently generates tweet ideas from user-provided content, with minor user-review notes for URL fetching, local output saving, and persuasive marketing language.

This skill appears safe for generating tweet ideas. Use it with content you are comfortable analyzing, be mindful that provided URLs may be fetched, and review the generated marketing language before publishing.

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.

Note

ASI02: Tool Misuse and Exploitation

What this means

The assistant may retrieve web pages you provide and create a local output file with generated tweet ideas.

Why it was flagged

The skill directs the agent to use a web-fetch tool for user-provided URLs and to write a generated markdown file. This is disclosed, user-directed, and aligned with creating tweet ideas from reference material.

Skill content

If the user provides a URL, use web_fetch to retrieve the content. ... Save to tweet-ideas/tweets-{timestamp}.md

Recommendation

Provide only URLs and source material you want analyzed, and review the saved output before using or sharing it.

Note

ASI09: Human-Agent Trust Exploitation

What this means

Generated tweets may include urgency, exclusivity, or status-oriented phrasing that sounds stronger than the original reference content.

Why it was flagged

The skill explicitly asks for persuasive marketing framing. This matches the social-media copywriting purpose, but generated claims could become overstated if not checked against the source material.

Skill content

Apply Psychological Triggers ... Time-bound promises ... Exclusivity framing ... Status elevation

Recommendation

Review generated ideas for factual accuracy, substantiation, and brand fit before publishing.