The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides an integration that reads data from Slack messages, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The Slack adapter in src/channels/slack.ts processes message.text from incoming events.
Boundary markers: There are no boundary markers or instructions to ignore embedded commands in the message processing logic.
Capability inventory: The skill is granted access to write_file, read_file, run_code, and install_pkg tools.
Sanitization: The raw content of the Slack message is passed directly to the message handler without filtering or escaping.
[EXTERNAL_DOWNLOADS]: Fetches the official Slack development framework from the standard package registry.
Evidence: npm install @slack/bolt in Step 3.
[COMMAND_EXECUTION]: Executes shell commands to install necessary dependencies for the Slack integration.
Evidence: The skill uses npm install to set up the @slack/bolt package.

add-slack