agentcard@0.2.0
CAUTION· install onlyPublisher claims: "Virtual MasterCards for AI agents — crypto payments, USDC wallet, create and manage virtual payment cards autonomously via x402 protocol on Stellar blockchain." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Telegram Bot API URL; Agent configured for autonomous execution without human approval. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
{ command: "support", description: "🧑💻 Support" },Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.this.baseUrl = `https://api.telegram.org/bot${token}`;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."Create a new virtual debit card. Pays on-chain with USDC via x402 protocol — fully autonomous, no human intervention needed. Returns card details (PAN, CVV, expiry) in the response.",Fix: Declare and request only the permissions the task needs.* @asgcard/mcp-server — Wallet-authenticated HTTP clientFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.`Hint: copy api/.env.example to api/.env and fill in required values.\n`;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.npx @asgcard/cli onboard -yFix: Pin versions and sources; vendor anything fetched at install time.`/support — 🧑💻 Contact support\n` +Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.description: 'Designed for autonomous agents. No human-in-the-loop. Deterministic, stateless, fast.',Fix: Declare and request only the permissions the task needs.* @asgcard/mcp-server — Wallet-authenticated HTTP clientFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.if (cmd === "/support" || text.startsWith("🧑💻") || text === "Support") {Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.[{ text: "❓ FAQ's" }, { text: "🧑💻 Support" }],Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.${codeBlock(`claude mcp add asgcard -- npx -y @asgcard/mcp-server`, 'bash')}Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
- Unclaimed publisher≈ +8 on the totalClaim asgcompute: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.