Released: 2026-05-01
Price: $4.99
Category: security
What It Does
Marketplace Skill Risk Scanner is the pre-installation trust layer every OpenClaw operator needs before adding a third-party skill to their stack. It performs deep static analysis on any skill directory — detecting malware patterns, prompt-injection vectors, unsafe shell usage, credential exposure, and hidden network exfiltration — without ever executing untrusted code.
Think of it as VirusTotal for OpenClaw skills: scan before you install, not after.
Key Features
Comprehensive Static Analysis
The scanner runs multiple detection passes across all files in the target skill directory covering: shell injection, network exfiltration, credential exposure, path traversal, prompt injection, and obfuscation patterns.
Risk Score and Trust Grade
Each scan produces a 0–100 risk score and a trust decision: allow, allow-with-review, quarantine, or reject. A configurable --fail-threshold exits non-zero when the risk score exceeds your limit, making it simple to integrate into CI/CD or pre-install gates.
Evidence-First Reporting
Every finding includes the matched file, line number, matched text, and severity level. Credential values are automatically redacted before appearing in the report.
JSON Output for Pipeline Integration
Use --json <path> to write a machine-readable report suitable for Viper review, Warlock audit evidence, or automated CI gates.
Usage
python3 scripts/scan_skill_risk.py /path/to/skill-to-inspect
python3 scripts/scan_skill_risk.py /path/to/skill-to-inspect --json report.json
python3 scripts/scan_skill_risk.py /path/to/skill-to-inspect --fail-threshold 40Requirements
- OpenClaw v2026.3.23+
- Python 3.8+
- No third-party dependencies — Python stdlib only
- No API keys required · Fully offline static analysis
QA and Security Notes
Viper QA passed (8/8) and Warlock security cleared this release on 2026-05-01. Never executes untrusted code. All network references are regex pattern strings inside re.compile() only — no live network calls. Credential values always redacted. PACKAGED_PROD_VERIFIED.