script creator with github companion

Create and modify scripts in ~/.nanobot/workspace/test with strict Git versioning. Each script lives in its own directory with an isolated git repository. Al...

Before installing or using this skill, consider: 1) Name mismatch — the skill title suggests GitHub integration but the instructions only perform local git operations; ask the author whether GitHub push/pull and credential use are intended. 2) Missing declarations — the metadata does not list required binaries (git, python, pip) or handle a missing virtualenv; verify those tools and the venv exist or request the skill be updated to create/validate them. 3) Pip installs — the skill will run pip install in the venv and therefore will download and execute third-party package code (PyPI or other indexes); only proceed with packages you trust or require a lockfile/explicit package list. 4) Confirm behavior — the SKILL.md insists on explicit user confirmation before changes; when enabling autonomous invocation for an agent, ensure the agent will not bypass that confirmation. 5) If you need GitHub remote support, ask the developer to add explicit, documented steps for pushing to remotes and to declare the GitHub credential requirements. Overall the skill appears coherent for local script/git management but has enough omissions and a misleading name that you should request clarifications/changes before trusting it with important files.

Type: OpenClaw Skill Name: script-creator Version: 1.0.0 The skill's stated purpose of managing scripts with Git is benign, and its instructions to the AI agent include strong security constraints. However, the `SKILL.md` instructions implicitly create a critical shell injection vulnerability. The agent is instructed to directly substitute user-provided inputs (e.g., `<script_name>`, `<extension>`, `<package_name>`) into shell commands like `mkdir`, `touch`, `cd`, `pip install`, and `git commit` without any explicit guidance for sanitization. This allows a malicious user to inject arbitrary commands (e.g., `my_script; rm -rf /`) which the agent would then execute, leading to potential remote code execution. Additionally, the instruction to `pip install` user-specified packages introduces a supply chain risk, as malicious packages can execute arbitrary code during installation.