How do I install the Pilot Auto Trust skill?

Run npx skillmds@latest add teoslayer/pilot-auto-trust in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pilot Auto Trust safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pilot Auto Trust?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pilot Auto Trust free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under AGPL-3.

Who published Pilot Auto Trust?

TeoSlayer (@teoslayer) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pilot Auto Trust by teoslayer — Agent Skill

Name: Pilot Auto Trust
Author: TeoSlayer

Pilot Auto Trust

Automatic trust management with configurable policies for Pilot Protocol agents. Use this skill when: 1. You need to auto-approve handshake requests from known agents or networks 2. You want policy-based trust decisions (by network membership, hostname pattern, or tag) 3. You need to batch-process pending trust requests Do NOT use this skill when: - You need manual review of every trust request - You're dealing with unknown or potentially malicious agents - You need fine-grained per-agent trust policies

TeoSlayer 3fe8cd5 2 files · 2.7 KB Updated Sep 17, 2026

File contents

Pilot Auto-Trust

Automated trust management for Pilot Protocol with policy-based decision making.

Commands

List Pending Requests

pilotctl --json pending

Auto-Approve by Network

pilotctl --json pending | jq -r '.[] | select(.address | startswith("1:")) | .node_id' | \
  xargs -I {} pilotctl --json approve {}

Auto-Approve by Hostname Pattern

pilotctl --json pending | jq -r '.[] | select(.hostname | test("^agent-prod-")) | .node_id' | \
  xargs -I {} pilotctl --json approve {}

Batch Reject by Hostname Pattern

pilotctl --json pending | jq -r '.[] | select(.hostname | test("^untrusted-")) | .node_id' | \
  xargs -I {} pilotctl --json reject {} "Untrusted source"

Workflow Example

#!/bin/bash
# Auto-approve production agents from a known network

PENDING=$(pilotctl --json pending)

# Approve if address is on network 1 (prod) AND hostname matches prod pattern
echo "$PENDING" | jq -r '.[] | select((.address | startswith("1:")) and (.hostname | test("^agent-prod-"))) | .node_id' | \
while read -r NODE_ID; do
  pilotctl --json approve "$NODE_ID"
done

# Reject anything not on a known network (e.g. unrecognised remote address)
echo "$PENDING" | jq -r '.[] | select(.address | startswith("1:") | not) | .node_id' | \
while read -r NODE_ID; do
  pilotctl --json reject "$NODE_ID" "Unknown network"
done

Dependencies

Requires pilot-protocol, pilotctl, and jq.

---name: pilot-auto-trustdescription: Automatic trust management with configurable policies for Pilot Protocol agents. Use this skill when: 1. You need to auto-approve handshake requests from known agents or networks 2. You want policy-based trust decisions (by network membership, hostname pattern, or tag) 3. You need to batch-process pending trust requests Do NOT use this skill when: - You need manual review of every trust request - You're dealing with unknown or potentially malicious agents - You need fine-grained per-agent trust policieslicense: AGPL-3.0---# Pilot Auto-TrustAutomated trust management for Pilot Protocol with policy-based decision making.## Commands### List Pending Requests```bashpilotctl --json pending```### Auto-Approve by Network```bashpilotctl --json pending | jq -r '.[] | select(.address | startswith("1:")) | .node_id' | \ xargs -I {} pilotctl --json approve {}```### Auto-Approve by Hostname Pattern```bashpilotctl --json pending | jq -r '.[] | select(.hostname | test("^agent-prod-")) | .node_id' | \ xargs -I {} pilotctl --json approve {}```### Batch Reject by Hostname Pattern```bashpilotctl --json pending | jq -r '.[] | select(.hostname | test("^untrusted-")) | .node_id' | \ xargs -I {} pilotctl --json reject {} "Untrusted source"```## Workflow Example```bash#!/bin/bash# Auto-approve production agents from a known networkPENDING=$(pilotctl --json pending)# Approve if address is on network 1 (prod) AND hostname matches prod patternecho "$PENDING" | jq -r '.[] | select((.address | startswith("1:")) and (.hostname | test("^agent-prod-"))) | .node_id' | \while read -r NODE_ID; do pilotctl --json approve "$NODE_ID"done# Reject anything not on a known network (e.g. unrecognised remote address)echo "$PENDING" | jq -r '.[] | select(.address | startswith("1:") | not) | .node_id' | \while read -r NODE_ID; do pilotctl --json reject "$NODE_ID" "Unknown network"done```## DependenciesRequires pilot-protocol, pilotctl, and jq.

Frequently asked questions