Prompting

• Risk level: Low
• Analyzed: May 1, 2026, 5:45 AM
• Findings: 1
• Version: 1.0.0

Overview

This instruction-only prompt-writing skill is coherent and purpose-aligned, with a disclosed local memory file that users should understand before use.

This skill appears safe to install as an instruction-only prompting assistant. Be mindful that it asks to keep local memory in ~/prompting/memory.md, so do not place sensitive personal, business, or confidential writing samples there unless you are comfortable with them being reused in future prompting tasks.

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

Past preferences or corrections could be reused in later prompt-writing sessions, which is helpful for consistency but may preserve information the user did not intend to keep long term.

Why it was flagged

The skill creates persistent local memory for user preferences and correction history, which can influence future prompting tasks.

Skill content

Store in `~/prompting/memory.md`:
- User's preferred style (terse vs detailed)
- Target models they commonly use
- Past corrections

Recommendation

Review ~/prompting/memory.md periodically, avoid storing sensitive writing samples or private details there, and delete entries that should not affect future prompts.