ev-charger
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill performs network requests to api.getcamino.ai and suggests installation from an unverified GitHub repository (barneyjm/camino-skills). While functional, these are external dependencies outside the trusted scope.
- [COMMAND_EXECUTION] (SAFE): The provided shell script utilizes curl and jq. It correctly validates JSON input and uses jq for URI encoding of parameters, preventing common command injection vectors.
- [CREDENTIALS_UNSAFE] (SAFE): The skill requires a CAMINO_API_KEY but does not hardcode secrets. It follows best practices by using environment variables for authentication.
- [PROMPT_INJECTION] (LOW): The skill has an indirect prompt injection surface. 1. Ingestion points: Data is retrieved from the Camino AI API. 2. Boundary markers: No explicit boundary markers or ignore instructions are present in the script output. 3. Capability inventory: The skill can execute network requests via curl and parse data via jq. 4. Sanitization: Data is passed through jq for formatting, but no specific content sanitization for LLM instructions is performed.
Audit Metadata