pp-splitwise

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install software from the author's official repositories on GitHub (github.com/mvanhorn) and npm (@mvanhorn/printing-press-library). These are vendor-owned resources consistent with the skill's stated purpose.
  • [REMOTE_CODE_EXECUTION]: Installation involves executing remote code through 'npx' and 'go install' commands. This is the standard deployment mechanism for the Splitwise CLI tool and its associated MCP server.
  • [COMMAND_EXECUTION]: The skill operates by executing the 'splitwise-pp-cli' binary with various subcommands and arguments. It uses the 'Read Bash' tool to interact with the local environment.
  • [DATA_EXFILTRATION]: The CLI tool includes a '--deliver webhook:' flag that allows command output to be sent to arbitrary external URLs. While this is a documented feature for automation, it creates a potential path for data exfiltration if an agent is directed to use an untrusted URL.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:59 PM
Security Audit — agent-trust-hub — pp-splitwise