lnurl-auth

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly allows and demonstrates passing a private key as a command-line argument (--key <hex> / example with <64-char-hex-private-key>), which requires the LLM/user to supply and could cause the model to emit secret values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.30). In lnurl_auth/mcp/server runtime, the tool accepts attacker-supplied lnurl and then performs a challenge GET and parses the response body as JSON (and later returns the server response), meaning outsider-authored text from the service callback/challenge can be ingested without selecting a specific item first.