The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the help-scout-pp-cli and help-scout-pp-mcp tools from the author's GitHub repository (github.com/mvanhorn/printing-press-library) and via NPM (@mvanhorn/printing-press-library). These resources belong to the skill's author and are used for its core functionality.\n- [COMMAND_EXECUTION]: The skill relies on shell commands for the installation of prerequisites (npx, go install) and for its operational commands (help-scout-pp-cli).\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from the Help Scout API.\n
Ingestion points: Data is retrieved from Help Scout conversations, customers, and mailboxes via the CLI tools (e.g., in SKILL.md under the Command Reference section).\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore embedded instructions.\n
Capability inventory: The agent has access to the bash shell and the help-scout-pp-cli tool, which can perform further network operations and write to the local file system.\n
Sanitization: The instructions do not define any sanitization, filtering, or validation processes for the data retrieved from the Help Scout API.

pp-help-scout