newsletter-curation

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install additional components from the vendor's repository via 'npx skills add inference-sh/skills'. It also utilizes remote applications such as 'tavily/search-assistant' and 'exa/search' to perform network-based content searches.
  • [COMMAND_EXECUTION]: Employs the 'infsh' CLI for essential tasks including authentication and tool execution. These commands are part of the core functionality and are intended for direct execution by the user.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities when handling external content.
  • Ingestion points: Data is ingested from the internet via search tools ('tavily/search-assistant', 'exa/search') to provide content for newsletters.
  • Boundary markers: The provided curation templates lack specific delimiters or instructions to ignore potential commands embedded in the retrieved web content.
  • Capability inventory: The toolset includes capabilities for shell command execution through 'infsh' and social media interaction via 'x/post-create'.
  • Sanitization: There is no evidence of content sanitization or instruction filtering applied to the search results before they are processed for commentary and publication.
  • [NO_CODE]: The skill does not package any standalone executable scripts or source files, relying solely on markdown instructions and CLI command examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:30 PM