Spritz Fiat Rails

Off-ramp crypto to fiat bank accounts using the Spritz API. Use when an agent needs to send payments to bank accounts, convert crypto to fiat, execute off-ra...

This skill appears to implement the advertised off-ramp workflow, but there are important inconsistencies you should resolve before installing: (1) The documentation requires SPRITZ_API_KEY, but the registry metadata does not declare any required environment variables or primary credential — request that the publisher update metadata so the platform can show and gate the API key permission. (2) Remove or change examples that echo secrets (e.g., 'echo $SPRITZ_API_KEY') because printing secrets can leak them to logs; the skill's text even forbids logging the key, so this example contradicts that rule. (3) Because this skill moves real money, restrict autonomous invocation or ensure the platform enforces explicit user confirmation for every payment. (4) Verify the service domain (api.spritz.finance) and the identity of the publisher since 'Source' and 'Homepage' are missing. If the publisher can address the metadata/secret-handling issues and you can enforce mandatory confirmation policies, the skill's behavior is coherent; until then treat it cautiously.

Type: OpenClaw Skill Name: spritz-agentic-rails-skill Version: 0.1.1 The skill bundle is designed to facilitate crypto-to-fiat off-ramp payments via the Spritz API, a high-risk financial operation. However, the documentation, particularly `SKILL.md` and `references/security.md`, contains extensive and explicit instructions for the AI agent to follow robust security practices. These include mandatory user confirmation for all payments and bank account changes, strict API key protection, sensitive data sanitization, and detailed defenses against prompt injection attacks. All `curl` commands are directed to the legitimate `api.spritz.finance` endpoint for the skill's stated purpose, and there is no evidence of data exfiltration to unauthorized destinations, malicious execution, persistence mechanisms, or intentional harmful behavior. The skill's design prioritizes security and user validation, classifying it as benign despite the inherent risks of financial transactions.