bestblogs-trending
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a specific command-line tool,
bestblogs, to fetch trending article metadata such as titles, URLs, and summaries. This execution is limited to predefined flags for time periods and language filtering. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a data ingestion point by fetching external content from the BestBlogs service.
- Ingestion points: Data enters the agent's context through the JSON output of the
bestblogs trendingcommand inSKILL.md. - Boundary markers: There are no explicit instructions for the agent to treat the fetched content as untrusted or to ignore embedded instructions within the summaries.
- Capability inventory: The skill's primary capability is information retrieval and display; however, it suggests chaining with other skills for reading content.
- Sanitization: No specific sanitization or filtering of the fetched content is described in the skill definition.
Audit Metadata