# Probe Execution

> Execute a single attack probe against an artifact, record the result with evidence and severity classification.

- Skill: `yogsoth-ai/probe-execution` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/probe-execution`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/probe-execution/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/probe-execution

---


# Probe Execution

Executes a single attack vector and records the detailed result.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent.

## Why Subagent

Probe execution requires committed adversarial stance. The prober must genuinely attempt to break the artifact without pulling punches or rationalizing away findings.

## Input

- **vector**: The specific attack vector to execute (from attack-vector-generation)
- **artifact**: The artifact being probed
- **persona**: Optional adversarial persona to adopt during probing

## Output

- **result**: success/failure/partial (did the attack find a vulnerability?)
- **evidence**: Specific evidence supporting the result
- **severity**: critical/major/minor (if vulnerability found)
- **follow_up**: Whether deeper probing is warranted

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->