finding-aggregation

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/finding-aggregation

Aggregates and classifies probe findings into a structured vulnerability report

  • Reduces redundant findings and organizes them by severity and type
  • Uses subagent execution for neutral, cross-probe analysis
  • Identifies patterns and coverage gaps from attack metadata
  • Delivers prioritized recommendations for remediation

SKILL.md

.github/skills/finding-aggregationView on GitHub ↗
---
name: finding-aggregation
description: Aggregate, deduplicate, and classify findings from multiple probes into a coherent vulnerability report.
execution: subagent
prompt: ./prompt.md
input: findings (string), attack_metadata (string)
used-by: [red-teaming]
---

# Finding Aggregation

Synthesizes findings from multiple attack probes into a coherent, deduplicated report.

## Execution

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

## Why Subagent

Aggregation requires neutral analytical stance — neither inflating nor minimizing findings. The aggregator must see patterns across individual probe results.

## Input

- **findings**: All probe results from the campaign
- **attack_metadata**: Metadata about attack coverage (surfaces hit, vectors used, personas deployed)

## Output

- **vulnerabilities**: Deduplicated list classified by severity and type
- **patterns**: Cross-cutting patterns observed across multiple probes
- **coverage_gaps**: Surfaces or dimensions not adequately tested
- **recommendations**: Prioritized hardening actions

More from yogsoth-ai/de-anthropocentric-research-engine

SkillDescription
abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
ablation-component-mappingMap system architecture to ablatable units for ablation studies
ablation-designDesign ablation studies to isolate component contributions in ML systems
ablation-executionRemove components one by one from a system, record the response/impact of each removal.
abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
abstraction-ladderPerform bisociation at multiple abstraction levels
abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.