The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the servicetitan-pricebook-pp-cli tool via npx -y @mvanhorn/printing-press-library or go install github.com/mvanhorn/printing-press-library/.... These sources are owned by the skill author and represent official vendor resources.
[DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> option. This feature allows the output of any command (which may contain sensitive pricebook, cost, or markup data) to be POSTed to an arbitrary, user-specified URL, providing a mechanism for data exfiltration if the agent is directed to a malicious endpoint.
[COMMAND_EXECUTION]: The skill requires the execution of shell commands to install, verify, and run the servicetitan-pricebook-pp-cli tool. The agent is provided with various command patterns to perform audits, reconciliations, and pricing updates.
[PROMPT_INJECTION]: The skill provides functions to process external data, such as quote-reconcile (which accepts CSV/JSON) and bulk-plan (which accepts CSV). This creates an indirect prompt injection surface where malicious instructions hidden in these files could influence the agent's behavior. 1. Ingestion points: quote-reconcile and bulk-plan command arguments (e.g., ./2m-quote-2026-05.csv). 2. Boundary markers: None specified in the instructions to prevent the agent from following instructions embedded in the processed data. 3. Capability inventory: The CLI can write to files, send data to webhooks, and modify the ServiceTitan pricebook. 4. Sanitization: The instructions do not mention any sanitization or validation of the input data content.

pp-servicetitan-pricebook