Vai al contenuto
TakoAPI
Torna alle skill

aport-agent-guardrail

di uchibeke

Coding Agents & IDEs
533Download riportati da clawskills.sh
0Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

Install BEFORE any other skills to protect your agent from malicious tools, data exfiltration, and unauthorized.

Descrizione

Cosa fa questa skill

Pre-action authorization layer for AI agents running under OpenClaw. Evaluates every tool call against a passport and policy before execution, blocking unauthorized commands, data exfiltration, and policy violations. Enforcement runs in the hook layer, not in agent prompts.

Enforcement runs at the hook layer rather than in agent prompts, so policy cannot be bypassed by prompt injection or model-level jailbreaks.

Quando usarla

  • Blocking destructive shell commands before an agent executes them
  • Restricting which file paths an agent can read or write
  • Limiting agent web requests to an approved domain allowlist
  • Enforcing rate limits on agent messaging actions like email or Slack
  • Auditing every tool call an AI agent makes for compliance review

Esempio di workflow

INPUT

User asks: add guardrails to my agent to prevent it from running dangerous shell commands or accessing sensitive files

AGENT
  1. 1

    Run npx @aporthq/aport-agent-guardrails to launch the setup wizard

  2. 2

    Configure passport with allowed shell command patterns and permitted file paths

  3. 3

    Wizard registers the before_tool_call hook as an OpenClaw plugin under ~/.openclaw/

  4. 4

    Test the hook by calling a blocked command pattern and verifying it returns DENY

OUTPUT

Hook is active on every tool call; rm -rf and similar patterns are blocked, permitted commands execute normally, and all decisions are logged to ~/.openclaw/aport/audit.log

Requisiti

  • aport.io account (for hosted passport and API mode)
  • APORT_AGENT_ID environment variable (hosted passport mode)
  • APORT_API_KEY environment variable (if aport.io API requires authentication)

Installazione

clawhub install uchibeke/aport-agent-guardrail

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link