Skills
skills/qiniu/skills/miku-live/Gen Agent Trust Hub

miku-live

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands and scripts in multiple languages (JavaScript, Node.js, Go, Java, PHP) to interact with Qiniu Miku Live APIs.- [PROMPT_INJECTION]: The skill processes user-supplied data in params_json to construct API calls. Ingestion points: params_json and intent fields in SKILL.md and references/schemas.md. Boundary markers: Structured input validation using JSON schemas and the references/interface-catalog.md. Capability inventory: Execution of curl and language runtimes to perform API tasks. Sanitization: Mandatory mapping of intents to a verified interface catalog.- [SAFE]: Authentication credentials are handled via environment variables or parameters with explicit instructions to prevent their exposure in outputs. All API operations target official Qiniu domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 08:37 AM