Insert honeypot tokens into sensitive files to detect if an agent leaks their contents in output
原文语言:英语
菜单
SkillsMP 已收集 TheArchitectit/agent-guardrails-template 中的 13 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 13 / 13 个已收集 Skill。
Insert honeypot tokens into sensitive files to detect if an agent leaks their contents in output
原文语言:英语
Topic-based content filtering to block harmful or unauthorized content in agent output
原文语言:英语
Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.
原文语言:英语
Available guardrail tools and automatic enforcement behavior for pi agents
原文语言:英语
How to use and interpret the guardrails panel and status bar in the pi TUI
原文语言:英语
Detect and block prompt injection attacks in tool input (bash commands, write/edit content) before execution
原文语言:英语
Prevent sensitive data (secrets, credentials, PII) from leaking in agent output
原文语言:英语
How guardrail policies cascade from organization through team to project level
原文语言:英语
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation
原文语言:英语
Per-tool permission levels (auto/ask/blocked) that gate which tools the agent can use
原文语言:英语
Validates git commits follow COMMIT_WORKFLOW.md standards: AI attribution, single focus, no secrets
原文语言:英语
Enforces TEST_PRODUCTION_SEPARATION.md: production code first, separate instances, no data mixing
原文语言:英语
Enforces the Four Laws of Agent Safety automatically on all operations. Halts on uncertainty.
原文语言:英语