finder-reactor
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of markdown-based architectural documentation and conceptual state machine descriptions rather than executable scripts or tool implementations.
- [SAFE]: Implements a 'Guard > Speed' safety philosophy, explicitly requiring human intervention and confirmation before the system can perform external writes, high-cost operations, or handle ambiguous data.
- [SAFE]: Mandates strict data privacy through 'Fission' patterns, which involve pruning sensitive user data (like full CVs) and platform context before they are sent to large language models.
- [SAFE]: External references are limited to the author's own GitHub repository (p10ns11y) and relative links to other architectural skills, presenting no third-party supply chain risks.
- [SAFE]: Provides a detailed surplus log documenting the transition to a local SQLite-based persistence layer for auditability and history, which uses standard libraries without suspicious execution patterns.
Audit Metadata