The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the slack-pp-cli and slack-pp-mcp tools.
Binaries are downloaded from the author's GitHub repository (github.com/mvanhorn/printing-press-library) via go install.
An installer is fetched from the NPM registry using npx -y @mvanhorn/printing-press.
These external resources originate from the identified skill author's infrastructure.
[COMMAND_EXECUTION]: The skill uses local command execution to perform Slack operations.
Executes slack-pp-cli for tasks such as searching messages, listing users, and analyzing workspace activity.
Invokes claude mcp add to register the MCP server with the agent environment.
[PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection due to its interaction with external workspace data.
Ingestion points: Data enters the agent context via slack-pp-cli commands that read Slack message history, channel content, and thread data (e.g., search, digest, sync).
Boundary markers: The instructions do not define specific delimiters or security headers to isolate Slack data from the agent's core instructions.
Capability inventory: The agent has the ability to execute further CLI commands and network requests based on the content it parses from Slack.
Sanitization: There is no evidence of data sanitization or instruction filtering applied to the messages retrieved from the Slack API.

pp-slack