Steep FrameworkSAFE
Overview
An agent skill published by revfactory.
459e1bb8f76eOBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: steep-framework
description: "A STEEP macro-environment analysis methodology for systematic identification of scenario planning variables. Used by the variable-analyst agent for comprehensive environmental scanning. Automatically applied in contexts such as 'STEEP analysis', 'macro-environment analysis', 'environmental scanning', 'driving forces', 'megatrends'. However, real-time data collection and econometric model construction are outside the scope of this skill."
---
# STEEP Framework — Macro-Environment Analysis Tool
A specialized skill that enhances the environmental scanning capabilities of the variable-analyst agent.
## Target Agent
- **variable-analyst** — Systematic identification of key variables using the STEEP framework
## STEEP 6-Dimension Scanning
### Dimension Definitions
| Dimension | Scope | Example Variables |
|-----------|-------|-------------------|
| **S** Social | Demographics, lifestyle, values, education | Aging population, remote work adoption, DEI awareness |
| **T** Technological | Innovation, adoption rate, disruption | AI adoption, quantum computing, cybersecurity threats |
| **E** Economic | Growth, inflation, trade, labor market | Interest rate changes, supply chain restructuring, gig economy |
| **E** Environmental | Climate, resources, sustainability | Carbon regulation, ESG pressure, resource scarcity |
| **P** Political | Government policy, regulation, geopolitics | Data privacy regulation, trade wars, political polarization |
| **L** Legal | Laws, compliance, intellectual property | Antitrust regulation, labor law changes, patent disputes |
### Scanning Checklist per Dimension
For each dimension, investigate:
1. **Current State**: What is happening now?
2. **Direction of Change**: Which way is the trend moving?
3. **Speed of Change**: How fast? (Gradual/Rapid/Discontinuous)
4. **Certainty**: Is this predetermined or uncertain?
5. **Impact**: How does it affect our industry/organization?
## Uncertainty-Impact Matrix
### 4-Quadrant Classification
```
Impact (High)
| Q2: Predetermined Q1: Scenario Drivers
| (Certain Trends) (Matrix Axes)
| → Apply to all → 2 axes for matrix
| scenarios
|
| Q4: Background Q3: Monitor
| (Ignore) (Wild Cards)
| → Minimal attention → Watch list
|
Impact (Low)
+--- Uncertainty (Low) ---- Uncertainty (High)
```
### Assessment Criteria
| Score | Uncertainty | Impact |
|-------|-----------|--------|
| 5 | Completely unpredictable, multiple possible outcomes | Existential impact on business model |
| 4 | Difficult to predict, 2-3 plausible outcomes | Significant impact on core revenue |
| 3 | Somewhat predictable but variable | Moderate impact on operations |
| 2 | Mostly predictable with minor variations | Limited departmental impact |
| 1 | Nearly certain, single expected outcome | Negligible impact |
## Trend Classification
### Predetermined Trends
- High certainty of direction (uncertainty score 1-2)
- Applied as constants across all scenarios
- Example: Aging population in developed nations
### Critical Uncertainties
- High uncertainty AND high impact (Q1 quadrant)
- Used as scenario matrix axes
- Example: AI regulation direction (restrictive vs. permissive)
### Wild Cards
- Low probability but potentially high impact events
- Included as shock events within specific scenarios
- Example: Pandemic, technology breakthrough, geopolitical crisisTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
459e1bb8f76efull audit observations/trust-audit/skill/revfactory__steep-framework.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 459e1bb8f76e | SAFE | B | 89 | first audit |
Questions
Is Steep Framework safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Steep Framework access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (459e1bb8f76e), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.