The Agent Skills Directory

[COMMAND_EXECUTION]: The skill functions by executing the slack-cli binary and piping its output to other shell utilities like jq, sed, base64, and curl for data processing and API interaction.
[EXTERNAL_DOWNLOADS]: The instructions direct the user to install a third-party binary using brew install paymog/tap/slack-cli. This introduces a dependency on the vendor's repository and build infrastructure.
[CREDENTIALS_UNSAFE]: The skill requires highly sensitive Slack API tokens (OAuth xoxp/xoxb or session tokens xoxc/xoxd) to be provided as environment variables or stored in local auth profiles. These credentials grant broad read/write access to the Slack workspace.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text data from external Slack conversations.
Ingestion points: Data is fetched via conversations history, conversations search, conversations unreads, and users search, pulling arbitrary user-generated message text into the agent's active context.
Boundary markers: The skill body does not specify the use of delimiters or 'ignore' instructions to separate Slack content from the agent's core instructions.
Capability inventory: The skill possesses capabilities for network operations (via the binary and curl), file system writes (attachments get -o path), and message posting.
Sanitization: There is no explicit sanitization or filtering of the retrieved Slack content before it is presented to the LLM.

slack-cli