Get the FREE Ultimate OpenClaw Setup Guide โ†’
p

Pincer

Verified

@panzacoder

npx machina-cli add skill @panzacoder/pincer --openclaw
Files (1)
SKILL.md
7.0 KB

pincer ๐Ÿ›ก๏ธ

Security-first wrapper for clawhub install. Scans skills for malware, prompt injection, and suspicious patterns before installation.

Why?

Agent skills are powerful โ€” they're basically executable documentation. The ClawHub ecosystem has already seen malware campaigns distributing infostealers via innocent-looking skills. pincer adds a security layer before you install anything.

Install

# From ClawHub
clawhub install pincer

# Or manually
chmod +x ./scripts/pincer.sh
ln -sf "$(pwd)/scripts/pincer.sh" ~/.local/bin/pincer

Dependencies:

  • clawhub โ€” for fetching skills
  • uvx โ€” for mcp-scan (brew install uv)
  • jq โ€” for JSON parsing

Usage

Safe Install

# Instead of: clawhub install some-skill
pincer install some-skill

# With specific version
pincer install some-skill@1.2.0

Scan Without Installing

# Scan a ClawHub skill
pincer scan some-skill

# Scan a local directory
pincer scan ./path/to/skill

# JSON output for automation
pincer scan some-skill --json

Audit Installed Skills

# Quick-scan all installed skills
pincer audit

# JSON output
pincer audit --json

Manage Trust

# Add trusted publisher (auto-approve clean skills)
pincer trust add steipete

# Remove from trusted
pincer trust remove old-publisher

# Block a publisher or skill
pincer trust block suspicious-dev
pincer trust block malware-skill

# Unblock
pincer trust unblock redeemed-dev

# List all trust settings
pincer trust list

View History

# See what you've installed
pincer history

# JSON output
pincer history --json

Configuration

# Show current config
pincer config show

# Edit in $EDITOR
pincer config edit

# Reset to defaults
pincer config reset

What It Checks

Via mcp-scan (Invariant Labs)

  • Prompt injection attacks
  • Malware payloads in natural language
  • Tool poisoning
  • Sensitive data exposure
  • Hard-coded secrets

Additional Pattern Detection

PatternRiskDescription
Base64 commands๐Ÿšจ HighEncoded shell commands
Hex payloads๐Ÿšจ HighObfuscated binary data
xattr -d quarantine๐Ÿšจ HighmacOS Gatekeeper bypass
curl | sh๐Ÿšจ HighPipe to shell execution
Password archives๐Ÿšจ HighHidden malicious payloads
Download + executeโš ๏ธ Mediumchmod +x && ./ patterns
eval $varโš ๏ธ MediumDynamic code execution
Hidden filesโš ๏ธ MediumDot-file creation
Persistenceโš ๏ธ Mediumcron/launchd entries

Publisher & Provenance

  • Publisher reputation (trusted list)
  • Download count threshold
  • Skill age threshold
  • Blocklist checking

Binary Detection

  • Scans for bundled executables
  • Flags Mach-O, ELF, PE32 binaries

Risk Levels

LevelMeaningAction
โœ… CLEANNo issuesAuto-approve if trusted publisher
โš ๏ธ CAUTIONWarnings presentPrompt for approval
๐Ÿšจ DANGERSuspicious patternsBlock (override with --force)
โ˜ ๏ธ MALWAREKnown maliciousBlock (cannot override)
โ›” BLOCKEDOn blocklistBlock (cannot override)

Configuration

Config: ~/.config/pincer/config.json

{
  "trustedPublishers": ["openclaw", "steipete", "invariantlabs-ai"],
  "blockedPublishers": [],
  "blockedSkills": [],
  "autoApprove": "clean",
  "logInstalls": true,
  "minDownloads": 0,
  "minAgeDays": 0
}
KeyDescription
trustedPublishersPublishers whose clean skills auto-approve
blockedPublishersAlways block these publishers
blockedSkillsAlways block these specific skills
autoApprove"clean" = auto-approve clean+trusted, "never" = always prompt
logInstallsLog installations to history file
minDownloadsWarn if skill has fewer downloads
minAgeDaysWarn if skill is newer than N days

Examples

Clean Install

$ pincer install bird
๐Ÿ›ก๏ธ pincer v1.0.0

  โ†’ Fetching bird from ClawHub...
  Publisher: steipete (trusted)
  Stats: 7363 downloads ยท 27 โ˜… ยท created 1 month ago

๐Ÿ›ก๏ธ pincer Scanning bird...

  โ†’ Running mcp-scan...
  โœ… mcp-scan: passed
  โ†’ Checking for suspicious patterns...
  โœ… Pattern check: passed
  โ†’ Checking external URLs...
  โœ… URL check: passed
  โ†’ Checking for bundled binaries...
  โœ… Binary check: passed

Risk Assessment:
  โœ… CLEAN โ€” No issues detected

  โ†’ Auto-approved (clean + trusted config).
  โ†’ Installing bird...
  โœ… Installed successfully!

Dangerous Skill Blocked

$ pincer install sketchy-tool
๐Ÿ›ก๏ธ pincer v1.0.0

  โ†’ Fetching sketchy-tool from ClawHub...
  Publisher: newaccount (unknown)
  Stats: 12 downloads ยท 0 โ˜… ยท created 2 days ago

๐Ÿ›ก๏ธ pincer Scanning sketchy-tool...

  โ†’ Running mcp-scan...
  ๐Ÿšจ mcp-scan: high-risk warnings
  โ†’ Checking for suspicious patterns...
  ๐Ÿšจ Pattern check: suspicious patterns found
    โ€ข curl/wget piped to shell
    โ€ข macOS quarantine removal (xattr)
  โ†’ Checking external URLs...
  โš ๏ธ URL check: external URLs found
    โ€ข http://sketchy-domain.xyz/install
  โ†’ Checking for bundled binaries...
  โœ… Binary check: passed

Risk Assessment:
  ๐Ÿšจ DANGER โ€” Suspicious patterns detected
    โ€ข mcp-scan: high-risk patterns detected
    โ€ข curl/wget piped to shell
    โ€ข macOS quarantine removal (xattr)

  โ˜ ๏ธ Install blocked. Use --force to override (not recommended).

Credits

License

MIT


Stay safe out there. ๐Ÿ›ก๏ธ

Source

git clone https://clawhub.ai/panzacoder/pincerView on GitHub

Overview

Pincer adds a security layer before installing agent skills. It wraps clawhub install and scans for malware, prompt injection, and suspicious patterns prior to installation. This reduces risk from compromised or malicious skills.

How This Skill Works

Pincer uses mcp-scan (via Invariant Labs) to inspect skill payloads and patterns, flagging risks such as malware, prompt injections, and hard-coded secrets. It provides commands for safe install, scan, and audit, plus trust management and JSON outputs for automation. A local script is installed to PATH for easy access.

When to Use It

  • Before installing any new ClawHub skill to ensure safety
  • When auditing all installed skills for threats
  • When scanning a local skill directory before install
  • During publisher trust management to auto-approve clean skills
  • In automation pipelines needing JSON output for security checks

Quick Start

  1. Step 1: Install pincer to PATH (chmod +x scripts/pincer.sh and symlink to ~/.local/bin/pincer)
  2. Step 2: pincer install some-skill to safely install after scanning
  3. Step 3: Optional: pincer audit or pincer scan for ongoing safety

Best Practices

  • Always run pincer scan before pincer install
  • Run pincer audit regularly on installed skills
  • Maintain a trusted publishers list and block suspicious ones
  • Verify dependencies (clawhub, uvx, jq) are up to date
  • Use JSON output for CI/CD automation

Example Use Cases

  • Install a new skill safely by running pincer install my-skill
  • Scan a local directory before adding it to your environment
  • Audit all installed skills to detect hidden threats
  • Manage publishers by adding a trusted source with pincer trust add
  • Review install history to track changes

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers โ†—