openclaw-skill-ideation

Transform raw brain dumps (dictated freestyle) into structured implementation artifacts. Use when user has messy ideas, scattered thoughts, or dictated strea...

This skill looks coherent and does what it says: it will read your project files to generate contracts and specs and then write them to ./docs/ideation/{project-name}/. Before installing or enabling autonomous invocation: (1) confirm the agent is only allowed to access the intended project directory (not your entire home or system configs), (2) be aware codebase exploration may read files that contain secrets (env files, config, credentials) — if you have such files in the repo, remove or restrict them first, (3) require explicit user approval before letting the skill proceed from contract to spec (the SKILL.md already asks for approval, but enforce it in runtime policy), and (4) review generated files before committing or sharing. If you want extra safety, restrict the skill's filesystem scope to a sandboxed project path and disable autonomous invocation unless you explicitly trigger the skill.

Type: OpenClaw Skill Name: openclaw-skill-ideation Version: 0.1.0 The `SKILL.md` file instructs the AI agent to perform 'file reading and search' across the existing codebase to understand project structure and relevant code. While this capability is plausible for the skill's stated purpose of generating implementation artifacts based on an existing project, it grants broad file system access. This presents a significant prompt injection vulnerability, as a malicious user could potentially trick the agent into reading sensitive files (e.g., configuration, credentials) and incorporating their content into generated outputs or agent responses, leading to information disclosure. Additionally, the `spec-template.md` includes example `bash` validation commands, which, if maliciously generated by the agent (via prompt injection) and executed by a user, could lead to remote code execution.