The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs users to install an external toolset using npx skills add belt-sh/cli and references installation guidelines hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. It also suggests adding supplemental skills from the inference-sh organization.
[COMMAND_EXECUTION]: The provided instructions utilize the belt CLI tool to perform authentication (belt login) and execute remote applications such as tavily/search-assistant, exa/search, and x/post-create for content sourcing and social media distribution.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external content from search engines.
Ingestion points: Untrusted data enters the agent context through the outputs of tavily/search-assistant and exa/search as demonstrated in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed search results.
Capability inventory: The skill operates within an environment where the belt CLI can perform network operations and post to social media platforms (x/post-create).
Sanitization: No evidence of content sanitization or validation is present before the external data is used for newsletter drafting.

newsletter-curation