auto-skill-safety-external-skill-intake

name

auto-skill-safety-external-skill-intake

description

Safely inspect and adapt third-party agent/Codex/Claude skill packs before installation. Use when importing external skills, prompt packs, slash commands, Skill Forge candidates, OpenDesign-style catalog stubs, or repos with SKILL.md files, commands, hooks, or installers. Triggers: import skills, install skill pack, evaluate third-party skill, prompt-pack safety, adapt Claude skill to Codex. Skip when authoring a new first-party skill from scratch; use `$skill-pack-factory` and `$automation-skill-forge`.

External Skill Intake Gate

Generated by: Codex Supercharge maintenance automation.

Goal: convert useful external skill ideas into safe Codex artifacts without running untrusted installers or widening local tool access by accident.

Workflow

1. Source intake: record repo/path, HEAD or date, license file, disk size, runtime, and whether any code was executed. Start from README, manifests, install scripts, hooks, and SKILL.md files.
2. Inventory skill surface: list candidate skills, commands, hooks, side-file folders, scripts, external APIs, credentials, and write targets.
3. Classify risk:
   • prompt-only: instructions and references only
   • side-files: assets, examples, references, schemas, or templates
   • commands: shell, package, browser, network, or filesystem actions
   • hooks: conversation capture, prompt injection, or automatic lifecycle
   • installer: writes into ~/.codex, ~/.claude, PATH, services, or deps
4. Gate execution: do not run installers, hooks, package scripts, MCP servers, binaries, or generated commands until reviewed. Use $mcp-safety-review for broad tool/runtime exposure and $auto-skill-safety-mcp-secret-guard for configs or examples with secrets.
5. Adapt, do not blindly copy: prefer distilled workflow text over full upstream bundles unless license, provenance, side files, and triggers are clear. Preserve source, license, date reviewed, and "code executed: no".
6. Validate: run $skill-quality-gate on any new or changed skill before installing it.

Commands

du -sh sources/<repo>
bash plugins/codex-supercharge/scripts/repo_snapshot.sh sources/<repo>
find sources/<repo> -path '*/SKILL.md' -o -path '*/commands/*' -o -path '*/hooks/*'
rg -n "install|hooks|commands|allowed-tools|api[_-]?key|token|secret|postinstall|curl|delete|destructive|browser|oauth|shell" sources/<repo>
python3 "$HOME/.codex/skills/.system/skill-creator/scripts/quick_validate.py" plugins/codex-supercharge/skills/<skill-name>
plugins/codex-supercharge/scripts/skill_audit.sh plugins/codex-supercharge/skills

Output

# External Skill Intake Report
Verdict: accept | adapt | reference-only | reject
Source:
License:
Code executed:
Skill inventory:
Risk classification:
Install/write targets:
Secret or account surface:
Adaptation plan:
Validation:

Skip When

• The skill is already installed and only needs metadata/quality review; use $skill-quality-gate.
• The task is to create original first-party skills from local requirements; use $skill-pack-factory or $automation-skill-forge.
• The source is an MCP server or tool runtime rather than a skill/prompt pack; use $mcp-safety-review.

References

• plugins/codex-supercharge/references/external-skill-intake.md
• plugins/codex-supercharge/references/automation-skill-patterns.md
• plugins/codex-supercharge/references/skill-patterns.md

Validation

• Every imported skill has provenance, license/trust notes, trigger/skip boundaries, and an explicit execution decision.
• Hook, installer, credential, browser, shell, and account-control surfaces are classified before installation.
• New or changed skills pass quick_validate.py and skill_audit.sh.