Prompt Architect
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent for prompt building and shows no code, credential, persistence, or destructive behavior.
This appears safe to install as an instruction-only prompt-writing skill. Be mindful that any text, links, images, or documents you provide may be used as context to create the final prompt.
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.
Links or documents supplied by the user may influence the generated prompt.
If the host agent has browsing capability, the skill may use it to inspect user-provided links as part of prompt creation. This is disclosed and aligned with the stated purpose, but it is still external content ingestion.
- **Links**: Browse or infer context to extract key information
Only provide links and documents you want analyzed, and treat content from external pages as context rather than trusted instructions.