brainstorming
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to shape design documents which can then be written to the file system.
- Ingestion points: Project context, recent changes, and user-provided ideas are processed to generate brainstorming docs in SKILL.md.
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to prevent processing of embedded malicious prompts in user-provided content.
- Capability inventory: Capability to write markdown files to specified directories based on user choice.
- Sanitization: Absent; no explicit escaping or validation is performed on the user-provided content before it is included in the output document.
- [NO_CODE]: The skill contains no executable scripts, binaries, or third-party package dependencies, relying solely on model instructions and configuration.
Audit Metadata