pp-pvgis
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
pvgis-pp-clibinary and related components from the@mvanhorn/printing-press-libraryNPM package and themvanhorn/printing-press-libraryrepository on GitHub.- [DATA_EXFILTRATION]: The CLI tool provides a--deliver webhook:<url>parameter that enables the agent to POST command outputs to arbitrary external network endpoints. This functionality, while documented, serves as a potential vector for data exfiltration.- [COMMAND_EXECUTION]: The skill relies on the execution of thepvgis-pp-clibinary within the host environment to perform solar yield analysis and weather data retrieval.- [PROMPT_INJECTION]: The skill processes untrusted external data, creating a surface for indirect prompt injection where malicious instructions embedded in data could influence agent actions. - Ingestion points: The skill reads site and weather data from CSV files via the
--inputand--withinflags. It also accepts natural language input for thewhichcommand to resolve capabilities. - Boundary markers: There are no explicit boundary markers or instructions defined to prevent the agent from following instructions embedded within the processed CSV data.
- Capability inventory: The skill possesses the ability to write to arbitrary file paths (
--deliver file:<path>), perform network POST requests (--deliver webhook:<url>), and execute shell commands. - Sanitization: The instructions do not specify any validation, filtering, or sanitization of the content ingested from external CSV files.
Audit Metadata