The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the belt CLI (via the Bash tool) to perform operations such as authenticated login, social media posting (x/post-create), image generation (infsh/html-to-image), and web browsing (infsh/agent-browser).
[EXTERNAL_DOWNLOADS]: The documentation references the installation of the belt-sh/cli package via npx and provides links to configuration/installation guides hosted on GitHub (inference-sh/skills).
[PROMPT_INJECTION]: The skill establishes a workflow where untrusted data from external sources is ingested and used in automated tasks, creating a surface for indirect prompt injection:
Ingestion points: External data enters the agent context through the tavily/search-assistant and infsh/agent-browser tools.
Boundary markers: The provided instructions do not include explicit delimiters or 'ignore embedded instructions' warnings for processing the retrieved content.
Capability inventory: The agent has the capability to write to the local terminal and execute social media posts via belt app run x/post-create.
Sanitization: There are no documented sanitization or validation steps for the data retrieved from search results before it is incorporated into post content.

twitter-thread-creation