pp-expensify

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Downloads and installs the expensify-pp-cli and expensify-pp-mcp tools from the author's (mvanhorn) GitHub and NPM repositories.
  • [DATA_EXFILTRATION]: Provides a --deliver webhook:<url> flag which allows the CLI to send command output—potentially containing sensitive financial or expense information—to any external URL.
  • [CREDENTIALS_UNSAFE]: Manages Expensify authentication by storing session tokens and integration keys in local files like credentials.toml and config.toml.
  • [COMMAND_EXECUTION]: Executes local binaries to perform expense filing, reporting, and database management, requiring access to the local file system and Expensify's API.
  • [PROMPT_INJECTION]: Processes untrusted external data (CSV strings and natural language prompts) to generate expense entries.
  • Ingestion points: expense quick, expense from-line, and expense bulk command arguments.
  • Boundary markers: None present in the provided instructions to delimit external content.
  • Capability inventory: Performing network requests (Expensify API, webhooks) and writing to local databases and configuration files.
  • Sanitization: No sanitization or validation of the ingested external data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:59 PM
Security Audit — agent-trust-hub — pp-expensify