Quick overview
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.
Common tasks
- 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
Install paths
Primary command
openclaw install oliveskin/agent-tinman
ClawHub installer
npx clawhub@latest install oliveskin/agent-tinman
OpenClaw CLI
openclaw skills install oliveskin/agent-tinman
Direct OpenClaw install
openclaw install oliveskin/agent-tinman
Skill metadata
- Category: Calendar & Scheduling
- Language: Markdown
- Version: 0.6.4
- Security status: Benign
Review upstream source
The full public SKILL.md body is not directly fetchable for this entry right now, so this page is using the best available catalog metadata. Review the upstream source page for the latest files, version history, and security scan details: https://clawhub.ai/oliveskin/agent-tinman
