No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by vahta-team · Agent Tool · ★ 71
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is vahta safe to install? View the security audit →
key-amnesia ### key-amnesia is now Vahta Vahta lets your AI agent use your passwords and API keys — without ever letting it see them. The product and the concept are tested. What comes next is not an iteration but a hard reboot: a deep refactor onto a new core, which is why the project has been renamed and moved here. Faster, and more reliable, on more platforms — with enterprise-grade quality and the features small and medium teams actually need. Individual developers stay a first-class priority rather than an afterthought, because the mission is safe autonomous long-running agents for everyone, and security is a baseline, not a luxury. Everything below still describes the software as it ships today. remains installable from PyPI and will get one final release. It will never be yanked, so pinned installs keep working. Let your AI agent use your passwords and API keys — without ever letting it see them. , in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: