cli-anything-novita
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external AI models (Novita AI, DeepSeek, GLM), which presents a surface for indirect prompt injection.
- Ingestion points: Output from the
chatandstreamsubcommands (SKILL.md). - Boundary markers: The skill does not define specific delimiters or "ignore" instructions for processed model data.
- Capability inventory: The CLI supports configuration writes (
config set) and network connectivity to the Novita AI API (SKILL.md). - Sanitization: No specific filtering or sanitization of model output is documented.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
cli-anything-novitaPython package. - Resource: Installation via
pip install cli-anything-novita. As a vendor-owned resource for 'hkuds', this is standard installation procedure. - [COMMAND_EXECUTION]: The skill functions as a CLI harness, requiring the agent to execute system commands to interact with the Novita AI service (SKILL.md).
Audit Metadata