agent-tinman
oliveskin 제작
Calendar & Scheduling요약
AI security scanner with active prevention - 168 detection.
설명
이 스킬이 하는 일
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.
사용 시점
- 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
예시 워크플로
User asks: Scan the last 48 hours of sessions for security issues
- 1
Run /tinman scan --hours 48 to analyze recent sessions
- 2
Check sessions for prompt injection, tool misuse, and context bleed
- 3
Classify each finding by severity S0-S4
- 4
Write findings to ~/.openclaw/workspace/tinman-findings.md
- 5
Run /tinman report --full to display results with evidence and mitigations
Findings report listing detected issues by severity, with evidence snippets and mapped mitigations for each
설치
clawhub install oliveskin/agent-tinmanCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.