build-persona

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands (via Bash) to execute python3 scripts for processing large JSON datasets fetched from the Readwise API. This is a performance optimization to avoid context window limits and is scoped to data analysis.
  • [DYNAMIC_EXECUTION]: The skill generates and executes a single-use Python script at runtime to parse, summarize, and extract patterns (such as site frequency, save velocity, and highlight samples) from the retrieved Readwise data.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the user's personal data (highlights, document metadata, and tags) from Readwise via MCP tools or the readwise CLI. These operations are within the stated purpose of the skill and target the vendor's own services.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:50 AM
Security Audit — agent-trust-hub — build-persona