pp-zoho-expense

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install a CLI tool from a vendor-owned GitHub repository and the npm registry.
  • Evidence: npx -y @mvanhorn/printing-press-library install zoho-expense --cli-only and go install github.com/mvanhorn/printing-press-library/library/productivity/zoho-expense/cmd/zoho-expense-pp-cli@latest.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the zoho-expense-pp-cli binary to perform its core functions.
  • [DATA_EXFILTRATION]: A significant exfiltration risk is present via the --deliver webhook:<url> flag, which allows routing all command output to an arbitrary external endpoint.
  • [CREDENTIALS_UNSAFE]: The skill documentation explicitly notes that OAuth refresh tokens are stored in the local file system at ~/.config/zoho-expense-pp-cli/config.toml.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data from invoices and receipts.
  • Ingestion points: invoice ingest and receipt upload commands in SKILL.md process user-provided files and directories.
  • Boundary markers: None identified in the prompt templates.
  • Capability inventory: The skill can execute shell commands via the CLI and perform network operations including API calls and webhook delivery.
  • Sanitization: No explicit sanitization or validation of the ingested invoice content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:26 PM
Security Audit — agent-trust-hub — pp-zoho-expense