pp-shelters

Warn

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the shelters-pp-cli and shelters-pp-mcp binaries directly from the vendor's GitHub repository (github.com/mvanhorn/printing-press-library) using go install and npx.
  • [DATA_EXFILTRATION]: All commands supported by the CLI include a --deliver webhook:<url> flag. This allows an agent to POST the results of its operations, which could include sensitive location-based analysis or environment details, to any remote HTTP endpoint.
  • [DATA_EXFILTRATION]: The feedback command is designed to store data locally but can be configured via environment variables (SHELTERS_FEEDBACK_ENDPOINT and SHELTERS_FEEDBACK_AUTO_SEND) to automatically transmit content to a remote server.
  • [COMMAND_EXECUTION]: The CLI tool provides a --deliver file:<path> sink that allows the agent to write command output directly to any path on the local filesystem that the agent has permissions to access.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage profiles, install dependencies, and run diagnostics (shelters-pp-cli doctor), providing a broad surface for command-line interaction.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 19, 2026, 05:58 PM
Security Audit — agent-trust-hub — pp-shelters