ai-persona-os Security Audit Report
🔭 Continuously monitored by ClawSecure Watchtower
ai-persona-os is a Other skill for the OpenClaw ecosystem, created by jeffjhunter. ClawSecure audited this skill through our 3-Layer Audit Protocol covering all 10 OWASP ASI Top 10 categories. This skill received a security score of 0/100, indicating significant security concerns that require attention. The audit identified 66 findings, with issues detected across multiple security layers.
3-Layer Audit Protocol
Security Recommendations for ai-persona-os
Pin npm dependencies to exact versions
Unpinned dependencies allow supply chain attacks where a compromised package version is automatically pulled into your skill. Use exact version numbers in package.json (e.g.,
1.2.3 instead of ^1.2.3) to prevent unauthorized code from entering your dependency tree. ClawSecure's supply chain scanning checks every dependency against known CVE databases.Add a config.json permissions manifest
A config.json file declares what permissions your OpenClaw skill needs — file system access, network requests, shell execution, and more. Without it, users have no visibility into what your skill can do before installing. Adding a permissions manifest is the single most impactful security improvement for any OpenClaw skill.
Investigate prompt injection vectors
Prompt injection is one of the most critical threats to AI agent skills. Attackers can embed malicious instructions in content that your skill processes, causing it to take unintended actions. Review all points where your skill processes external content and implement input validation and output filtering.
Related OpenClaw Security Research
The Sleeper Agent Problem: Why Post-Install Behavior Matters→41% of Popular OpenClaw Skills Have Security Vulnerabilities→Related Other Security Audits
Scanned on March 3, 2026. ai-persona-os is one of 2,890+ agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.