extract-design-rationale
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration files. It defines a workflow for documentation and analysis without any executable scripts or tool invocations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project artifacts, which constitutes a data ingestion surface.
- Ingestion points: User-provided project notes, logs, specifications, and research (SKILL.md).
- Boundary markers: No explicit delimiters or boundary instructions are defined to separate untrusted data.
- Capability inventory: No tool access, subprocess calls, network operations, or file system modifications are present in the skill.
- Sanitization: No input validation or sanitization mechanisms are implemented.
Audit Metadata