research-boards
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for information retrieval and summarization from well-known and reputable technical sources such as Espressif, STMicroelectronics, and Adafruit. Its operations are restricted to searching and fetching public web content.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites, which is an untrusted input source. However, the potential risk is minimal as the skill lacks high-privilege capabilities.
- Ingestion points: Data is retrieved via WebSearch and WebFetch tools from manufacturer newsrooms and technical blogs listed in the SKILL.md file.
- Boundary markers: The instructions do not define specific delimiters for fetched content, but they enforce a rigid technical template for the final output, which naturally constrains the influence of injected content.
- Capability inventory: The skill is limited to
WebFetchandWebSearchtools. It does not have access to the file system, shell execution, or sensitive environment variables. - Sanitization: No explicit sanitization of fetched web content is performed before processing.
Audit Metadata