pp-kit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the
kit-pp-cliandkit-pp-mcptools. The installation methods includenpxfor the@mvanhorn/printing-press-librarypackage andgo installfor the repository located atgithub.com/mvanhorn/printing-press-library. These resources are managed by the skill vendor. - [COMMAND_EXECUTION]: The skill requires the use of the
Bashtool to execute thekit-pp-clibinary. This tool is used to perform account audits, manage broadcasts, and process subscriber data through the Kit API. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Kit API, including subscriber details, email snippets, and broadcast content. This external data is untrusted and represents a potential vector for indirect prompt injection if it contains instructions designed to manipulate the agent's logic.
- Ingestion points: Kit API responses for subscriber dossieres, content inventories, and account snapshots (SKILL.md).
- Boundary markers: The skill documentation does not define explicit boundary markers or warnings to the agent to ignore instructions embedded in API data.
- Capability inventory: The agent has the ability to execute shell commands via
Bash, write files locally using the--deliver file:<path>flag, and send data to external webhooks via the--deliver webhook:<url>flag. - Sanitization: No sanitization or escaping mechanisms for API data are documented in the skill instructions.
Audit Metadata