install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/andrewandrewsen/messageguard" ~/.claude/skills/openclaw-skills-messageguard && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/andrewandrewsen/messageguard" ~/.openclaw/skills/openclaw-skills-messageguard && rm -rf "$T"
manifest:
skills/andrewandrewsen/messageguard/SKILL.mdsource content
MessageGuard: Outgoing Message Filter Skill
Purpose: MessageGuard filters outgoing text to prevent secret leaks and sensitive data exposure by using pattern-based detection and configurable actions (mask, block, or warn).
Advanced Configuration Options:
: Determines the global action for matched patterns. Options are:mode
: Replace sensitive data with themask
.mask_char
: Prevent the message from being sent entirely.block
: Allow the message but generate warnings.warn
: The character(s) used to replace sensitive content whenmask_char
is set tomode
.mask
: Define or customize regex-based detections. Built-ins exist for API keys, credentials, and more (e.g., AWS keys, JWTs). Add new patterns based on your requirements.patterns
: Enable detections to be logged as structured JSON for monitoring, debugging, or compliance needs. Configure thelogging
for the output location.log_path- Custom Patterns: Users can define their custom patterns to override built-ins or extend functionalities. This supports regex and granular action control (mask, block, warn).
Installation
- Clone the repository:
.git clone git@github.com:AndrewAndrewsen/MessageGuard.git - Navigate to the directory. The skill is dependency-free, relying only on the Python standard library.