Technical Doc Generator

Generate professional technical documentation from codebases — API docs, READMEs, architecture diagrams, changelogs, and onboarding guides. Use when writing docs, creating API documentation, or delivering documentation projects.

This skill appears coherent and focused on scanning a codebase to produce docs. Before running it: (1) run it only on repositories you control or on a copied/sanitized snapshot — don't point it at / or your home directory; (2) avoid giving it repos that contain secrets or credentials (it may read .env.example or any file in the path); (3) if you want to limit risk, run in a sandboxed environment with no network access so it cannot fetch external resources; (4) verify generated outputs before publishing (it may infer authentication or configuration details that you should confirm). If you need absolute assurance, ask the skill author for explicit required binaries (e.g., git) and a more constrained instruction set.

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.