The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch content from external search engines (Tavily, Exa) to curate newsletter items. This process ingests untrusted third-party data that could contain malicious instructions designed to influence the agent's commentary or social media generation.
Ingestion points: SKILL.md references the use of tavily/search-assistant and exa/search to gather industry news and trending discussions.
Capability inventory: The agent uses the gathered data to generate summaries, write editorial commentary, and create social media posts via x/post-create.
Boundary markers: The provided templates do not include specific delimiters or instructions to ignore embedded commands within the search results.
Sanitization: There are no explicit steps for sanitizing or filtering external content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the belt CLI tool to run various applications for content discovery, image generation, and social media posting. The allowed-tools configuration specifically enables shell access for these tasks.
[EXTERNAL_DOWNLOADS]: The documentation points to external GitHub resources for installation guides and additional skill dependencies within the inference.sh ecosystem.

newsletter-curation