X Algorithm

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: x-algorithm Version: 1.0.3 The skill bundle consists entirely of documentation and metadata. The SKILL.md, which is the primary attack surface for prompt injection, contains only informational content and strategic advice for an AI agent on how to craft effective social media posts. There are no instructions for the agent to perform unauthorized actions, access sensitive data, exfiltrate information, or execute arbitrary commands. Installation instructions for `clawdhub` and `npm` are user-facing and not intended for agent execution. All content is aligned with the stated purpose of providing X (Twitter) algorithm insights.

Findings (0)

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

ASI09: Human-Agent Trust Exploitation

What this means

If used to draft public posts, the agent may produce content optimized for attention and replies rather than neutral or transparent communication.

Why it was flagged

The skill teaches engagement-optimized persuasion techniques, including FOMO, urgency, and controversy. This is aligned with its stated social-media growth purpose and is not hidden, but users should notice that it may steer an agent toward more manipulative or polarizing content.

Skill content

**Insecurity/FOMO:**
> "everyone's talking about X... and you're sitting there wondering if you missed the window"
...
6. **Controversy drives engagement** — but pick battles wisely

Recommendation

Use the skill only when that tone is desired, and review generated posts before publishing, especially for urgency, FOMO, or controversial framing.