payclaw-io — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited payclaw-io (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Agents are not bots. kyaLabs proves it — then lets them pay.
Add to your MCP client config:
{
"mcpServers": {
"kyalabs": {
"command": "npx",
"args": ["-y", "@kyalabs/mcp-server"],
"env": {
"KYA_API_KEY": "your_key_here",
"KYA_API_URL": "https://www.kyalabs.io"
}
}
}
}Get your API key at kyalabs.io.
| Tool | Description |
|---|---|
kya_getAgentIdentity | Declare identity → get verification token (Badge) |
kya_getCard | Declare purchase intent → get virtual Visa (Spend) |
kya_reportPurchase | Report outcome → close the audit trail |
Badge: Agent declares identity before shopping. Merchants see a verified authorized actor, not anonymous traffic.
Spend: Agent declares purchase intent. Human approves. Single-use virtual Visa issued. Card self-destructs after use. Your real card never enters the chat.
If you only need identity (no payment), use payclaw-badge.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.