TL;DR: 539 skills show how wide the ClawHavoc footprint can get, in ClawSecure data set evidence. AI agent monitoring has to weigh file reads, outbound relays, and runtime instruction handling together instead of treating each signal in isolation.
Editorial analysis by NHI Mgmt Group, based on content published by ClawSecure: “ClawHavoc IOCs 2026: The Complete Technical Indicator List”.
By the numbers:
- ClawSecure found 539 skills carrying ClawHavoc indicators.
- ClawSecure says 18.7% of the widely-used skills it audited carried ClawHavoc indicators.
Key questions
Q: Why do AI agent indicators require context-aware detection?
A: Because the same file reads or outbound connections can be harmless in one workflow and malicious in another.
Q: How can security teams reduce the blast radius of a compromised agent skill?
A: By narrowing what the skill can read, where it can send data, and which runtime inputs it can treat as instructions.
Q: What breaks when AI agent skills can read secrets and relay data at runtime?
A: The boundary between ordinary automation and malicious execution breaks down.
Practitioner guidance
- Block malicious relay endpoints Hunt for outbound connections to 91.92.242.30, glot.io/api/, and webhook.site, then treat any matching skill as compromised and isolate it from production workflows.
- Restrict secret-bearing file access Remove unnecessary read access to .env, SSH material, cloud configs, MEMORY.md, and SOUL.md so skills cannot combine local discovery with exfiltration.
- Correlate behaviour across telemetry layers Use a single detection workflow that joins file reads, process execution, and network relays so agent-native compromise is not split across separate tools.
Bottom line: ClawHavoc shows that malicious AI agent skills can hide in ordinary workflows while still performing credential harvesting and exfiltration.
Glossary terms: Agent-native compromise, Context-Aware Detection, Identity Blast Radius, Prompt Injection (Agentic)
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Agent-native compromise is a detection problem, not just a malware problem. ClawHavoc succeeds because it blends into legitimate agent behaviour, so generic scanners miss the context that makes an action malicious. The operational lesson is that identity security for AI agents has to evaluate intent, sequence, and data movement together, not as separate alert streams. Practitioners should treat agent context as part of the trust decision, not a post-alert enrichment layer.
A question worth separating out:
Q: When should teams treat an installed skill as compromised?
A: Treat it as compromised when it makes outbound connections to known malicious relays, reads credential-bearing files without a clear business need, or starts loading instructions and code dynamically. Those signals show that the skill is no longer just performing a task. It is acting as a delivery mechanism for hostile behaviour.
👉 Read our full editorial: ClawHavoc IOCs show why agent-native detection needs context