The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external installation script and documentation hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[REMOTE_CODE_EXECUTION]: The instructions prompt the user to install and execute external code packages from repositories such as belt-sh/cli and inference-sh/skills using the npx skills add command. These are non-standard sources for code execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external search assistants (Tavily and Exa) via the belt CLI tool.
Ingestion points: Data returned from belt app run for research and fact-checking purposes in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential malicious prompts embedded within search results.
Capability inventory: The skill has access to shell execution via the Bash(belt *) tool specified in the allowed-tools frontmatter.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external search providers before it is processed by the agent.

press-release-writing