Перейти к содержимому
TakoAPI
Назад к навыкам

agent-tinman

от oliveskin

Calendar & Scheduling
2.9kЧисло загрузок по данным clawskills.sh
3Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

AI security scanner with active prevention - 168 detection.

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

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

АГЕНТ
  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

ВЫВОД

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

Установка

clawhub install oliveskin/agent-tinman

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки