pp-open-meteo

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the open-meteo-pp-cli tool from the vendor's GitHub and NPM repositories using go install and npx.
  • [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> parameter, enabling the transmission of command outputs to arbitrary external network endpoints. Additionally, the feedback command allows sending notes to a configurable remote endpoint via the OPEN_METEO_FEEDBACK_ENDPOINT environment variable.
  • [COMMAND_EXECUTION]: The skill utilizes the open-meteo-pp-cli binary to perform various operations, including the capability to write results directly to local files via the --deliver file:<path> option.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external data from the Open-Meteo API.
  • Ingestion points: Data enters the agent context from Open-Meteo API endpoints (forecast, archive, air-quality, etc.) via the CLI tool (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions are present in the skill instructions.
  • Capability inventory: The CLI tool possesses capabilities for network egress (webhooks) and local file system modification (SKILL.md).
  • Sanitization: The instructions do not specify any sanitization or validation of the content received from the external API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 06:02 PM
Security Audit — agent-trust-hub — pp-open-meteo