pp-makerworld

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the makerworld-pp-cli tool using npx -y @mvanhorn/printing-press-library or go install github.com/mvanhorn/printing-press-library/.... These resources are managed by the skill's author.
  • [COMMAND_EXECUTION]: The skill requires the execution of shell commands to install, verify, and run the makerworld-pp-cli binary. It handles user arguments via a $ARGUMENTS pattern to determine whether to perform an installation or execute a search command.
  • [DATA_EXFILTRATION]: The CLI tool documented in the skill includes a --deliver webhook:<url> flag, which allows the agent to POST command results directly to a remote URL. While a legitimate automation feature, it represents a data routing capability that should be monitored.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill fetches and processes external 3D model data (titles, tags, descriptions) from the MakerWorld public catalog (SKILL.md).
  • Boundary markers: The skill uses the --agent flag to ensure output is delivered in a structured JSON envelope, which helps distinguish data from instructions.
  • Capability inventory: The skill has the ability to execute shell commands via the Read Bash tool.
  • Sanitization: There is no mention of sanitization for the external catalog content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:56 PM
Security Audit — agent-trust-hub — pp-makerworld