newsletter-curation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides references for installing the infsh CLI from the official inference-sh GitHub repository. This is a standard setup procedure for the platform's ecosystem.
  • [COMMAND_EXECUTION]: Uses the infsh command to run applications for searching (tavily/search-assistant, exa/search), media generation, and social posting. Access is restricted to the platform CLI via the allowed-tools frontmatter configuration, adhering to the principle of least privilege.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from external web searches.
  • Ingestion points: Data enters the context through tavily/search-assistant and exa/search tool outputs.
  • Boundary markers: Not explicitly defined in the curation instructions.
  • Capability inventory: Includes the ability to post content to social media platforms and generate images based on processed data.
  • Sanitization: The skill relies on the user's editorial curation to filter and validate content before distribution, which serves as a natural human-in-the-loop security control.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:26 PM