name: little-steve-agent-guard version: 0.1.4 description: Little Steve Agent Guard: a self-evolving security system for agent skills. Wraps all skill commands with risk assessment, audit logging, approval levels, and continuous rule evolution. / 小史安全卫士：面向 Agent Skill 的自进化安全系统。为所有技能命令提供风险评估、审计日志、分级审批和持续规则进化。 homepage: https://github.com/EchoOfZion/little-steve-agent-guard requires: bins: - jq

Little Steve Agent Guard

A self-evolving security system for agent skills. Wraps all skill command execution with risk assessment, audit logging, tiered approval, and continuous rule learning.

Dependencies

• jq (required) — install via brew install jq or apt install jq

Filesystem Scope

This is a cross-skill security guard. By design, it needs read access to other skills' directories to:

• guard-exec.sh: read target scripts for static risk analysis before execution
• capability-diff.sh: compare a skill's SKILL.md declarations against its actual scripts

The guard does not write to other skills' directories. All writes (audit logs, rules) stay within its own reports/ and rules/ directories.

Bypass & Emergency Procedures

The runbook (docs/runbook.md) documents emergency bypass procedures (circuit-break, manual script execution, log reset). These are human-operator-only actions for when the guard itself malfunctions. The agent must never execute bypass procedures autonomously.

CRITICAL: Execution Rule

ALL skill script executions MUST go through guard-exec.sh. Never call skill scripts directly. Always use:

bash {baseDir}/scripts/guard-exec.sh exec <script-path> [args...]

Example:

bash {baseDir}/scripts/guard-exec.sh exec {workspaceDir}/skills/<other-skill>/scripts/<script>.sh <command> [args...]

Approval Levels

• L1 (low/medium risk): Auto-execute, audit logged
• L2 (dry-run): Preview without executing
• L3 (high risk): Block and prompt user — output warning, wait for user to reply "确认" or "confirm"
• BLOCK (critical): Reject entirely, no execution possible

When guard-exec.sh returns exit code 10 (prompt), present the warning to the user and wait for confirmation. On "确认"/"confirm", re-run with confirm instead of exec.

Agent Command Conventions

1. Execute a skill command (with guard)

bash {baseDir}/scripts/guard-exec.sh exec <script> [args...]

2. Confirm a prompted action (after user approval)

bash {baseDir}/scripts/guard-exec.sh confirm <script> [args...]

3. Preview without executing

bash {baseDir}/scripts/guard-exec.sh dry-run <script> [args...]

4. Quick risk check

bash {baseDir}/scripts/guard-exec.sh check <script> [args...]

5. Run capability consistency check on a skill

bash {baseDir}/scripts/capability-diff.sh check --skill-dir <skill-path>

6. View audit stats

bash {baseDir}/scripts/audit.sh stats