ai-products
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches data from well-known services including Product Hunt, Hacker News (via Algolia API), and Techmeme, as well as an external RSS feed hosted on GitHub Pages.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: Product names, URLs, and descriptions are fetched via WebFetch from external sources in
SKILL.md. - Boundary markers: The skill does not define delimiters or instructions to ignore embedded commands within the fetched descriptions before processing them.
- Capability inventory: The skill has the capability to write the processed data into the local filesystem under the
50_资源/产品发布/directory as specified inSKILL.md. - Sanitization: There is no evidence of content sanitization or validation to ensure that the external text does not influence the agent's behavior or file-writing logic.
Audit Metadata