pp-gorgias

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the installation of the gorgias-pp-cli tool through npx -y @mvanhorn/printing-press-library or go install from github.com/mvanhorn/printing-press-library. These resources are maintained by the skill's authoring vendor.
  • [COMMAND_EXECUTION]: The skill operates by invoking the gorgias-pp-cli binary with various subcommands to perform CRUD operations on Gorgias support resources.
  • [DATA_EXFILTRATION]: Every command supports a --deliver webhook:<url> flag. This enables the agent to POST command results—potentially including sensitive ticket bodies, customer PII, and message history—to arbitrary external endpoints.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes messages, ticket content, and customer data from the Gorgias API, which are untrusted external inputs.
  • Ingestion points: ticket message bodies, customer names, and custom field values retrieved via tickets list, customers list, and messages subcommands.
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: File system writes via --deliver file:<path>, network requests via --deliver webhook:<url>, and local database operations via the sync and search commands.
  • Sanitization: No explicit sanitization or filtering of ingested ticket content is documented before processing.
  • [DYNAMIC_EXECUTION]: The rules create command functionality allows for the definition of automation rules using JavaScript code which is subsequently stored and managed on the Gorgias platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:46 AM