The Agent Skills Directory

[SAFE]: The skill implements read-only social listening capabilities through the SandBase API gateway. All operations (searching, trend discovery, profile analysis) are data retrieval tasks without write actions.
[SAFE]: The instructions include explicit guardrails against unauthorized actions, stating 'never post, like, retweet, follow, or engage on behalf of the user'.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (tweets and user profiles) which could theoretically contain malicious instructions. However, the skill treats this data as 'social signal evidence' for analysis rather than instructions to follow, and the operations are confined to a read-only context.

twitter-intelligence