newsletter-curation

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation guidelines from the inference-sh GitHub repository. This is a well-known service in this ecosystem and is used here for legitimate documentation purposes.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI to execute various applications for content sourcing and formatting, such as tavily/search-assistant, exa/search, and infsh/html-to-image. These commands are standard operations within the skill's defined purpose of newsletter creation.
  • [DATA_EXPOSURE]: This skill possesses an attack surface for indirect prompt injection as it processes external content from search engines and social media.
  • Ingestion points: External data enters the agent context via the output of belt app run for search tools (Tavily, Exa) in SKILL.md.
  • Boundary markers: No specific delimiters are defined in the instructions to separate search results from the system instructions.
  • Capability inventory: The skill has the capability to write files (newsletter templates) and post content to external platforms (via x/post-create).
  • Sanitization: The instructions do not define explicit sanitization; the skill relies on the agent's internal content filters when summarizing or processing search results.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:03 PM
Security Audit — agent-trust-hub — newsletter-curation