Back to skill
Skillv1.0.1
VirusTotal security
OpenClaw Guardian · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 29, 2026, 4:31 AM
- Hash
- d0e08b35417769ac68c80003efa9bfacd2173f63d56149cf0228a453d2fcd7d9
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: openclaw-guardian Version: 1.0.1 The OpenClaw Guardian skill bundle is designed as a security layer to intercept and verify dangerous tool calls, implementing a robust two-tier regex blacklist (`scripts/blacklist.ts`) and an LLM-based intent verification system (`scripts/llm-voter.ts`). While its intent is clearly defensive, the LLM verification component is susceptible to prompt injection. The `readRecentContext` function in `scripts/llm-voter.ts` feeds recent user messages directly to the LLM to determine if a dangerous action was explicitly requested. A sophisticated attacker could craft user messages that manipulate the LLM into confirming a blacklisted operation, thereby bypassing the intended security control. This constitutes a significant vulnerability, classifying the skill as suspicious rather than malicious, as the code itself is not designed for harmful behavior but contains a flaw that could be exploited.
- External report
- View on VirusTotal