agentshield
Before two agents exchange data, score one fresh model reply and require the peer key to sign it. Exit 2 means stop. Slug agentshield-audit.
as observed 2026-10-20T23:50:05.613Z- Identifier
agentshield-audit- Source
- ClawHub
- Version observed
- 1.6.5
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-10-13T16:37:28.889Z
- Observations recorded
- 2
- Installs (reported upstream)
- 68
- Weekly downloads (upstream)
- 3,094
- Declared license
- MIT-0
Observation history
2026-10-20T23:50:05.613Z
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v1.5.13 handshake and verify fixes" | "Score one fresh model reply before data exchange. The peer key must sign that reply." |
latestVersion |
"1.5.13" | "1.6.5" |
summary |
"Privacy-First security audit with 77 local tests (52 live + 25 static). Works with OpenClaw, Hermes Agent, n8n (auto-detected), LangChain, and any AI agent platform. Ed25519 priva | "Before two agents exchange data, score one fresh model reply and require the peer key to sign it. Exit 2 means stop. Slug agentshield-audit." |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.