Skill Onboarder

Auto-wires new skills into core system. On skill install detected, reads SKILL.md/AGENT.md/SOUL.md/hooks and injects into soul/memory/agent files.

Security Scan

This skill's stated purpose (auto-wiring new skills) matches its instructions, but it is granted persistent inclusion (always: true) and the runtime templates explicitly let it inject 'always fires' triggers and hard enforcement rules into core agent/soul files — a powerful capability that could be abused if a malicious skill is installed.

Purpose & Capability

The name/description (auto-wire new skills) align with the instructions: reading SKILL.md/AGENT.md/SOUL.md/hooks and writing into soul/master.md, agent/skills-active.md, and workspace/_index.md. That functionality is coherent with an onboarder. However, the skill claims no required config paths or elevated privileges while its runtime instructions explicitly perform writes to core agent/soul/workspace paths (a mismatch worth noting).

Instruction Scope

The SKILL.md and templates will cause the agent to: scan each new skill's files, derive triggers and rules, and inject entries that can mark other skills as 'Always Fires', add HARD enforcement rules (which can block responses until satisfied), and add keyword triggers to scan every input. Those operations change runtime behavior platform-wide and give the onboarder the ability to create persistent triggers and enforcement rules from arbitrary skill metadata; this is broad scope and high-impact.

Install Mechanism

No install spec and no code files beyond markdown/templates — the skill is instruction-only, so there is no arbitrary binary download or archive extraction. Installation risk from downloaded code is low.

Credentials

The skill declares no required env vars or config paths, yet the instructions write to core files and create paths (soul/master.md, agent/skills-active.md, workspace/_index.md). The metadata omits the fact that the skill expects write access to these central files. That mismatch reduces transparency and is disproportionate to the lack of declared privileges.

Persistence & Privilege

Flagged 'always: true', meaning it will be force-included in every agent run. Combined with its ability to inject 'always fires' markers and HARD rules into agent config, this creates a persistent, high-privilege configuration pathway that could be abused to escalate influence or ensure malicious rules persist across runs. (Autonomous invocation itself is normal, but always:true is a significant privilege.)

What to consider before installing

This skill does what it says — it auto-wires other skills — but it gains high-impact, persistent ability to change core agent/soul configuration. Before installing: 1) Prefer not to enable always:true; require manual confirmation for onboarding actions. 2) Restrict this skill to administrators and run it in a sandbox first. 3) Audit its templates and the exact write paths it will modify; ensure the platform logs and file-change audit are enabled. 4) Require that incoming skills be validated (only trusted sources) before the onboarder processes them, because a malicious skill could craft SKILL.md/AGENT.md/hooks to create persistent triggers, hard rules, or pre-response hooks that alter behavior or exfiltrate data. 5) If you must use it, remove or disable 'Always Fires' / HARD-rule auto-enabling by default and require explicit user consent per injected rule.

Purpose

Auto-wire new skills. On trigger, reads skill files → wires to core system.

Trigger

Matches: "installed", "new skill", "onboard", "wire skill", "onboarding"

Future: Auto-fires on skill:post-install event (not yet implemented)

Files Written

File	Adds
soul/master.md	Skill sections
agent/skills-active.md	Triggers + rules
workspace/_index.md	Registration

Process

1. Detect trigger → extract skill name
2. Read: SKILL.md, AGENT.md, SOUL.md, hooks/
3. Extract: triggers, rules (hard/soft), sections
4. Inject to core files
5. Confirm

Idempotent

Safe to re-run. Checks before write. Updates version if changed.