hive

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs users to set and store private keys directly (including via hive config set postingKey <private-key> and plaintext config.json), which requires including secret values verbatim in commands/files and thus poses exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and displays public, user-generated Hive blockchain content (e.g., via "hive content " and raw API calls to public nodes like https://api.hive.blog or arbitrary --node URLs), so it ingests untrusted third-party content that could carry indirect prompt injections.

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

• Direct money access detected (high risk: 1.00). The skill explicitly provides blockchain transaction broadcasting, including a "transfer" command for sending HIVE/HBD, and requires an "active" private key for transfers. It is specifically designed to sign and send crypto transactions (also supports custom JSON broadcasts), which grants direct financial execution authority on the Hive blockchain.