category-designer
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: This skill is documentation-only and does not contain any executable scripts, binaries, or subprocess calls. All logic is implemented via natural language instructions to the AI agent.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting untrusted data through external web searches and user-supplied product descriptions.
- Ingestion points: Step 1 in the workflow utilizes a
web_searchtool to analyze current market categories and competitor positioning. - Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from obeying instructions that might be embedded in the retrieved web content.
- Capability inventory: The skill is restricted to information gathering via
web_searchand text generation. It does not have access to file-system writes, sensitive credentials, or arbitrary code execution tools. - Sanitization: The skill lacks mechanisms to sanitize or validate external content before processing it for marketing strategy generation.
Audit Metadata