meta-design-expressive-typescript
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill directs the agent to ingest and analyze existing code files during the refactoring process, creating a surface for indirect prompt injection. This vulnerability arises when untrusted data (existing code) is processed by an agent with the capability to modify the project environment.
- Ingestion points: Existing project source code that the agent is instructed to read and refactor as per the core requirements in SKILL.md.
- Boundary markers: The skill does not define boundary markers or explicit instructions for the agent to ignore embedded commands within the analyzed code.
- Capability inventory: The agent is expected to perform file reading and code-writing operations.
- Sanitization: No validation or sanitization steps are provided to ensure the safety of the source material being processed.
Audit Metadata