Zum Inhalt springen
TakoAPI
Zurück zu den Skills

agent-tinman

von oliveskin

Calendar & Scheduling
2.9kDownloadzahlen laut clawskills.sh
3Sterne
0Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

AI security scanner with active prevention - 168 detection.

Beschreibung

Was dieser Skill macht

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.

Wann du ihn einsetzt

  • 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

Beispiel-Workflow

EINGABE

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

AGENT
  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

AUSGABE

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

Installation

clawhub install oliveskin/agent-tinman

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links