alby-bitcoin-payments

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

• Third-party content exposure detected (high risk: 0.80). This skill’s required workflow includes runtime fetching of outsider-authored free text from public sources via the discover/fetch flow (searching 402index.io and then consuming service URLs), whose retrieved page/body content can be fed back into the agent/LLM context as the “result” of fetch.

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

• Potentially malicious external URL detected (high risk: 1.00). The README instructs the agent to fetch and install the skill from https://getalby.com/payments/SKILL.md at runtime, which directly provides agent instructions/prompts and therefore is a remote dependency that controls the agent's behavior.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly a wallet/ payments CLI. It defines commands that send value (e.g. "pay" to lightning/BOLT-11/crypto addresses, "fetch" which pays HTTP 402 resources, hold/settle invoices, and other wallet operations) and requires a wallet connection secret to authorize these actions. These are specific financial-execution capabilities (sending payments, settling invoices, bridging rails), not generic tools.