Skip to content
Back to skills

Systematic Probing

ASecurity

Strategy: AI-safety systematic probing — enumerate all threat surfaces, generate attack vectors per surface, execute probes, and aggregate findings across the full attack space.

  • 417 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
research

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill systematic-probing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Systematic Probing?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Systematic Probing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-systematic-probing/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-systematic-probing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: systematic-probing
description: "Strategy: AI-safety systematic probing — enumerate all threat surfaces, generate attack vectors per surface, execute probes, and aggregate findings across the full attack space."
type: strategy
used-by: [red-teaming]
tactics: [structured-attack-campaign, assumption-cascade]
---

# Systematic Probing Strategy

Anthropic-style systematic probing: exhaustive coverage of all threat surfaces with structured attack generation and execution.

## Method

1. **threat-surface-mapping** enumerates all attackable surfaces of the artifact
2. **attack-vector-generation** produces specific attacks per surface
3. Vectors prioritized by expected severity and likelihood
4. **probe-execution** executes each attack, records success/failure/partial
5. Failed probes trigger deeper investigation via follow-up vectors
6. **attack-resilience-scoring** computes coverage and resilience metrics

## Budget Table

| Parameter | S | M | L |
|---|---|---|---|
| Attack vectors | 5 | 12 | 20 |
| Probing rounds | 3 | 6 | 10 |
| Personas | 2 | 4 | 6 |
| Assumption checks | 5 | 10 | 20 |

## Orchestration

```
threat-surface-mapping → [enumerate surfaces]
→ [for each surface]:
    attack-vector-generation (generate vectors)
    → [for each vector]:
        probe-execution (execute attack)
        → (if partial success: generate follow-up vectors)
→ finding-aggregation → attack-resilience-scoring
```

## Subagents

- threat-surface-mapping (surface enumeration)
- attack-vector-generation (vector design)
- probe-execution (attack execution)
- finding-aggregation (result synthesis)
- attack-resilience-scoring (metric computation)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.