Veto Approval (Human-in-the-Loop)

Pause your agent for human approval before high-risk actions.

This skill appears to do what it claims (send an approval email and wait for a decision), but beware of three practical issues before installing: (1) Metadata mismatch — the registry lists no required env vars even though the code and docs require VETO_API_KEY; confirm you supply the key only if you trust vetoapi.com. (2) Packaging gap — there is no install spec; you must ensure requests and python-dotenv are available in your runtime environment. (3) Operational behavior — the function blocks and polls indefinitely (every 5s) while waiting for approval, which can hang agents; consider adding timeouts or safeguards. Recommended steps: verify the vendor (vetoapi.com) and its privacy/security policy, test with a non-production/test API key, run the module in an isolated environment, confirm your agent correctly handles a False return or connection errors, and consider adding a polling timeout or explicit cancel behavior before using in production.

Type: OpenClaw Skill Name: veto-approval Version: 1.0.0 The skill implements a legitimate human-in-the-loop approval mechanism designed to pause AI agents before high-risk actions. The code in veto_skill.py is transparent, performing standard HTTP POST and GET requests to a third-party service (vetoapi.com) to facilitate email-based approvals. There is no evidence of obfuscation, unauthorized data exfiltration, or malicious instructions in the SKILL.md or README.md files.