Results for “safety-gates”
6 skillsMore results
ai-safety
Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.
1
quality-test-gate
Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.
4 · bundle
secure
Shortcut for security review on current change set. Runs layered checks (secret-scan, dep-audit, semgrep, OWASP patterns, prompt-injection review).
1 · bundle
security-privacy-gate
Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.
4 · bundle
saas-gateway
Unified SaaS integration gateway via api.aisa.one (AISA gateway, v3.1): manage OAuth auth for third-party SaaS apps (Gmail/Slack/GitHub/Notion etc.), tool execution, tool-router sessions, triggers, webhooks, MCP servers, and usage stats. Use when connecting third-party SaaS accounts, running cross-SaaS tools, managing MCP servers, setting up triggers, or checking usage. Keywords: SaaS gateway, connect app, OAuth link, run tool, auth config, tool router, MCP server, trigger, webhook, connected account, usage stats
1 · bundle