The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation references the use of npx skills add to install the inference-sh/skills package, which is a standard method for extending agent capabilities within this ecosystem.
[COMMAND_EXECUTION]: The skill utilizes the infsh CLI tool via Bash commands to interact with the Twitter/X API. This includes executing sub-commands like app run x/post-tweet and app run x/dm-send to perform its intended functions.
[DATA_EXFILTRATION]: The skill performs legitimate network operations to the inference.sh and Twitter/X APIs to transmit user-defined content, such as tweet text and direct messages, as part of its primary automation purpose.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes external text inputs (e.g., tweet content) which are then used in automated actions (posting to social media). While this creates a potential for the agent to be influenced by data it retrieves and subsequently posts, no specific malicious injection patterns were found in the static configuration.

twitter-automation