tempo

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow only reads first-party trusted Tempo service-discovery metadata via tempo wallet -t services (and then uses discovered URL/path for requests), and it does not include any step that ingests outsider-authored free text without first selecting a specific provider item.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs runtime installation with "curl -fsSL https://tempo.xyz/install -o /tmp/tempo_install.sh && ... bash /tmp/tempo_install.sh", which fetches and immediately executes remote code from https://tempo.xyz/install.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill exposes a CLI ("tempo") that includes wallet operations and automatic payment handling: it instructs agents to run tempo wallet login, check tempo wallet -t whoami, use tempo wallet fund, and it describes automatic payment handling when calling services (tempo request) and how to handle payment/funding errors. Those are explicit crypto/wallet financial actions (wallet login/funding, balance checks, and paying for service requests), which constitute direct financial execution capability.