Technical Doc Generator

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: technical-doc-generator Version: 1.0.0 The skill is classified as suspicious primarily due to the explicit inclusion of `Bash` in the `allowed-tools` list within `SKILL.md`. While the instructions themselves do not contain overtly malicious commands or prompt injection attempts, the ability to execute arbitrary shell commands (`Bash`) combined with broad file system access (reading codebases, config files like `.env.example`) presents a significant vulnerability. This capability could be exploited for remote code execution, data exfiltration, or other harmful actions if the agent's behavior is manipulated via prompt injection or if the skill were used by a malicious actor.

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.

What this means

If invoked on the wrong directory, it could read or modify more project files than intended.

Why it was flagged

The skill can inspect, modify, search, and run commands in the selected codebase. This is expected for documentation generation, but it is still broad local authority.

Skill content
allowed-tools: Read, Write, Edit, Grep, Glob, Bash
Recommendation

Run it from a version-controlled project directory, pass an explicit path when possible, and review generated diffs before committing or sharing.

What this means

Generated docs could expose internal design or configuration details to readers who receive the documentation.

Why it was flagged

The generated documentation may persist summaries of configuration, environment variable names, architecture, database schema, and dependencies. This is aligned with the skill purpose, but those details may be sensitive if the docs are shared externally.

Skill content
Configuration: [Detected from .env.example, config files, environment variables in code]
Recommendation

Review generated documentation for secrets, internal URLs, sensitive architecture details, and environment-specific values before publishing or sending it to clients.