genre-creator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the internet and writes it directly to the local file system, creating a vulnerability surface.
- Ingestion points: The skill uses the
WebSearchtool to gather facts about genre origins, pioneers, and albums from external websites (SKILL.md). - Boundary markers: There are no instructions to delimit or treat the external research data as potentially untrusted content.
- Capability inventory: The skill possesses
WriteandEditcapabilities, which are used to create directory structures and modify multiple files, including documentation (README.md,INDEX.md,genre-presets.md) and configuration files (genre-presets.yaml) (SKILL.md). - Sanitization: The skill lacks any sanitization, validation, or filtering mechanisms for the data retrieved via web search before it is interpolated into the project files.
Audit Metadata