add-expert
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of
bun render-cardswithin the project directory. This is a local development command used to generate static assets and is considered standard for this workflow. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of user-provided data (names, social links, and descriptions) into a source code file (
experts-data.tsx). - Ingestion points: User-provided expert metadata in SKILL.md.
- Boundary markers: None; user input is directly interpolated into a TypeScript code template.
- Capability inventory: Local file system write access and local script execution via
bun. - Sanitization: No sanitization or validation logic is specified for the expert description or social URLs.
Audit Metadata