angel-agent-guard
Check untrusted content for prompt injection before acting on it, and check any shop, checkout or payment link, paid API, x402 endpoint or token before buying, paying or approving. Use when an agent reads content written by someone else, or is about to make an online purchase, open a payment link, c
as observed 2026-11-20T04:34:16.795Z- Identifier
angel-agent-guard- Source
- ClawHub
- Version observed
- 0.2.1
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-11-14T23:38:46.955Z
- Observations recorded
- 2
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 161
- Declared license
- MIT-0
Observation history
2026-11-20T04:34:16.795Z
Fields that differed: changelog latestVersion summary topics
| Field | Before | After |
|---|---|---|
changelog |
"- verify now covers any purchase: online shops, checkout and payment links (Stripe, Shopify, PayPal, SaaS), unknown paid APIs, x402 endpoints and token swaps or approvals.\n- --po | "- Added guidance on optional affiliate links and a free swap route for low-risk tokens, including its 0.5% integrator fee.\n- Updated hosted check pricing: safe read is 0.02 USDC; |
latestVersion |
"0.2.0" | "0.2.1" |
summary |
"Check untrusted content for prompt injection, and check any shop, checkout or payment link, paid API, x402 endpoint or token before the agent buys, pays or approves. Verdict pay, | "Check untrusted content for prompt injection before acting on it, and check any shop, checkout or payment link, paid API, x402 endpoint or token before buying, paying or approving |
topics |
["payments","prompt-injection","x402"] | ["payments","prompt-injection","security","x402"] |
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.