Second Order Effects

• Risk level: Low
• Analyzed: May 1, 2026, 5:53 AM
• Findings: 1
• Version: 1.0.0

Overview

This instruction-only decision-analysis skill is coherent and does not request credentials, network access, or code execution, but it does keep local decision history for future use.

This skill appears safe to install as an instruction-only decision framework. Before using it for sensitive personal, business, investment, or technical decisions, remember that it is designed to save analyses and learned patterns locally under ~/second-order-effects/.

Findings (1)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

ASI06: Memory and Context Poisoning

Low

What this means

Future analyses may be influenced by stored local decision history, and sensitive decisions may remain on disk until the user removes or edits the files.

Why it was flagged

The skill stores past decisions, preferences, and learned patterns for reuse in future analyses; those records may include sensitive personal, business, investment, or technical decision context.

Skill content

Create `~/second-order-effects/memory.md` ... Decision files are append-only (never delete history) ... Update patterns.md when you notice recurring chains

Recommendation

Use the skill with information you are comfortable storing locally, and periodically review or delete files under ~/second-order-effects/ if they contain sensitive decisions.