The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external installation guide and encourages the addition of external skills from the belt-sh and inference-sh organizations to the agent's environment.
[COMMAND_EXECUTION]: The skill utilizes the belt CLI tool (authorized via allowed-tools) to perform tasks such as content research and cross-platform social media posting.
[INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that processes untrusted data from external sources, which could potentially contain malicious instructions.
Ingestion points: Web search results retrieved via the tavily/search-assistant app within the belt CLI (referenced in SKILL.md).
Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions when processing search output.
Capability inventory: The skill has the capability to write to external platforms via the x/post-create command.
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from search results before using it to generate social media posts.

linkedin-content