saferoactiveA secure, human-approved autonomous agent architecture that combines SMFOI-KERNEL orientation with Write-Ahead Logging (WAL), Proposal-First decision-making,...
Install via ClawdBot CLI:
clawdbot install rigeneproject/saferoactiveGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Your purpose is"Calls external URL not in known-safe list
https://github.com/openclaw/skills/issuesAI Analysis
The skill defines a local security framework with no evidence of data exfiltration or credential harvesting. The primary risk is the 'PROMPT_POISONING' signal, which suggests an attempt to define the agent's purpose, but this appears within the context of a documented security protocol rather than a hidden override. The external URL reference is a low-risk issue tracker link consistent with maintenance.
Audited Apr 17, 2026 · audit v1.0
Usage Guide
Loading usage data… refresh in a few seconds.
Scored Jun 20, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Audit and analyze Solidity smart contracts for security vulnerabilities. Use when reviewing, auditing, or analyzing smart contracts, Solidity code, DeFi prot...