Folders
v1.0.0Index important directories and perform safe folder operations with proper security checks.
⭐ 2· 989·1 current·1 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the runtime instructions: maintaining a local index (~/.config/folder-index.json), scanning common development/document folders, detecting project markers, and performing safe deletion semantics. No unrelated binaries, env vars, or network endpoints are requested.
Instruction Scope
Instructions are focused and constrained (scan limited set of likely paths, stop at first marker, don't recurse into large dirs, propose additions). However, the skill instructs filesystem discovery and deletion operations (using OS trash) which are inherently invasive — the SKILL.md generally requires user prompts for adding items but is less explicit about explicit confirmation for destructive bulk operations. Also assumes ability to canonicalize and skip symlinks; implementations must be careful to honor these rules.
Install Mechanism
No install spec and no code files — lowest risk: nothing is written to disk by an installer and nothing is downloaded or executed beyond what the host agent already does.
Credentials
The skill requests no credentials or environment variables, which is appropriate. It does require read/write access to the user's home config (~/.config/folder-index.json) and will traverse user directories (~/projects, ~/Documents, etc.). This is proportional to its purpose but is sensitive: the index and any scan results are local data that should be protected.
Persistence & Privilege
always:false and no system-wide config changes are requested, which is appropriate. The skill does write a persistent index file in the user's config directory — benign for this purpose — but if the agent is allowed to invoke skills autonomously, it could perform scans and update the index without frequent explicit user prompts. Consider controlling autonomous invocation or requiring explicit consent for bulk operations.
Assessment
This skill is internally consistent for indexing projects and doing safe folder operations, but it will scan parts of your home directory and write a persistent file at ~/.config/folder-index.json. Before installing, decide whether you trust the agent to access those folders and create/update the index automatically. Ask the maintainer (or your agent policy) to: require explicit confirmation before any bulk or destructive actions, restrict autonomous invocation if you don't want background scans, and store the index with appropriate file permissions. If you want to be extra cautious, back up or inspect ~/.config/folder-index.json after first use and run the skill in a limited environment (or with reduced folder scope).Like a lobster shell, security has layers — review code before you run it.
latestvk974gbrd1qd2jjk50gmdr4n4pn80zz96
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📂 Clawdis
OSLinux · macOS · Windows