pp-google-trends
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of external binaries and packages from vendor-controlled repositories, specifically github.com/mvanhorn/printing-press-library and the @mvanhorn/printing-press-library npm package.
- [COMMAND_EXECUTION]: The skill invokes the google-trends-pp-cli binary and provides instructions for installation via shell commands like go install and npx, requiring broad execution privileges within the runtime environment.
- [DATA_EXFILTRATION]: The CLI tool implements a --deliver webhook: feature, enabling the output of any command to be sent to an external URL via HTTP POST. This is a significant data exfiltration vector if the agent is directed to process sensitive data and route it through this tool.
- [CREDENTIALS_UNSAFE]: The auth login --chrome command allows the tool to import authentication cookies from the user's Chrome browser session. While intended for rate-limit bypass, this involves the access and storage of sensitive session identifiers.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the Google Trends API and local SQLite storage. 1. Ingestion points: Google Trends API responses and cached data in data.db. 2. Boundary markers: The skill utilizes JSON output for machine readability, but lacks explicit safety delimiters to isolate processed content. 3. Capability inventory: Execution of shell commands (google-trends-pp-cli), network POST requests via webhooks, and local file writes. 4. Sanitization: No specific content filtering or sanitization measures for external data are described.
Audit Metadata