pp-render
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing the
render-pp-clitool from the vendor's npm package (@mvanhorn/printing-press) or GitHub repository (github.com/mvanhorn/printing-press-library). - [COMMAND_EXECUTION]: The skill operates by running the
render-pp-clibinary, which can perform actions such as deleting services, databases, and disks. - [DATA_EXFILTRATION]: The tool includes a
--deliverflag to send output to webhooks and a feedback mechanism that can transmit data to a remote endpoint if configured. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection. 1. Ingestion points: Reads external data including logs, environment variables, and blueprints (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Can delete services, databases, and disks, and modify environment configurations (SKILL.md). 4. Sanitization: Absent.
Audit Metadata