← Back to Skills Marketplace
Safe Share
by
nighty35628
· GitHub ↗
· v1.0.0
· MIT-0
133
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install safe-share
Description
Sanitize logs, configs, prompts, stack traces, and skill content before they are shared publicly. Use when a user wants a local, low-risk pass to remove API...
Usage Guidance
This skill appears to do what it says: local deterministic sanitization with tests and no network calls or required credentials. Before installing or using it: (1) review the included sanitize_text.py to ensure its regex rules match your needs, (2) avoid using 'mask' mode when sanitizing very sensitive secrets because it preserves fragments, (3) run the smoke tests locally on representative samples, and (4) do not feed the sanitizer text you cannot disclose to local tooling unless you control the environment. If you want additional protections, add custom high-confidence patterns for any project-specific identifiers you need removed.
Capability Analysis
Type: OpenClaw Skill
Name: safe-share
Version: 1.0.0
The safe-share skill is a utility designed to sanitize sensitive information like API keys, tokens, and PII from text before public sharing. The implementation in scripts/sanitize_text.py uses deterministic regular expressions and local processing without any external network calls, data exfiltration, or obfuscation. The instructions in SKILL.md and the supporting documentation are well-aligned with the stated security-focused purpose.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, reference docs, tests, and the sanitize_text.py implementation all align: the skill's purpose is local sanitization of text before public sharing and the included code performs that function without requesting unrelated access.
Instruction Scope
SKILL.md instructs the agent to run the included scripts on the user-provided text and explicitly disallows sending text to external services or scanning unrelated files; the implementation follows that. Note: the sanitizer will read a file path if provided or stdin otherwise — it will not enumerate repositories unless the agent is explicitly asked to provide broader input scope.
Install Mechanism
No install spec or external downloads are present. This is an instruction-first skill with small local Python scripts and test files only, which is low-risk from an install/execution perspective.
Credentials
The skill requires no environment variables or credentials. One caution: the 'mask' mode intentionally preserves the first/last few characters of values, which can leak partial secret fragments; the SKILL.md documents mode choices, but users should avoid 'mask' for highly sensitive secrets.
Persistence & Privilege
The skill does not request persistent presence or elevated platform privileges (always:false). It does not modify other skills or system configuration and runs as a local script when invoked.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install safe-share - After installation, invoke the skill by name or use
/safe-share - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: local-first text sanitization for safe public sharing.
Metadata
Frequently Asked Questions
What is Safe Share?
Sanitize logs, configs, prompts, stack traces, and skill content before they are shared publicly. Use when a user wants a local, low-risk pass to remove API... It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install Safe Share?
Run "/install safe-share" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Safe Share free?
Yes, Safe Share is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Safe Share support?
Safe Share is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Safe Share?
It is built and maintained by nighty35628 (@nighty35628); the current version is v1.0.0.
More Skills