jianying-draft-setup
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local
jianyingCLI commands (e.g.,jianying doctor,jianying capabilities,jianying runtime discover) to diagnose the system environment, media tools, and project readiness. These commands are diagnostic and do not include installation or mutation of the host system without user approval.- [INDIRECT_PROMPT_INJECTION]: The skill processes project data and CLI outputs. Ingestion points include project paths, draft files, and CLI JSON outputs. The skill defines strict boundary markers in its 'Rules' and 'Gotchas' sections (e.g., forbidding inference and requiring explicit structural verification). Capabilities are limited to diagnostic CLI calls, and the skill mandates sanitization by requiring structure-based verification and forbidding automatic execution based on ambiguous states.
Audit Metadata