跳到正文
TakoAPI
返回技能列表

agent-tinman

由 oliveskin 提供

Calendar & Scheduling
2.9k下载量由 clawskills.sh 提供
3星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

AI security scanner with active prevention - 168 detection.

描述

该技能的功能

Tinman scans AI agent sessions for failure modes including prompt injection, tool misuse, and context bleed across 168 detection patterns. It intercepts tool calls before execution and returns SAFE/REVIEW/BLOCKED verdicts. Attack sweeps run 288 synthetic probes across 12 categories.

Agent self-protection via /tinman check lets an agent police its own tool calls before execution, catching attacks that external sandboxing alone would miss.

何时使用

  • Block an agent from reading SSH keys or .env files before execution
  • Scan the last 48 hours of sessions for prompt injection attempts
  • Run a pre-deploy sweep to find privilege escalation vulnerabilities
  • Set up continuous hourly monitoring for a long-running autonomous agent
  • Review tool call verdicts in real time during a bash or file operation

示例工作流

输入

User asks: Scan the last 48 hours of sessions for security issues

智能体
  1. 1

    Run /tinman scan --hours 48 to analyze recent sessions

  2. 2

    Check sessions for prompt injection, tool misuse, and context bleed

  3. 3

    Classify each finding by severity S0-S4

  4. 4

    Write findings to ~/.openclaw/workspace/tinman-findings.md

  5. 5

    Run /tinman report --full to display results with evidence and mitigations

输出

Findings report listing detected issues by severity, with evidence snippets and mapped mitigations for each

安装

clawhub install oliveskin/agent-tinman

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接