add-cdn-bundle

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides standard documentation-driven development instructions for internal repository modifications.
  • [COMMAND_EXECUTION]: Verification steps involve executing standard repository scripts (yarn lint, yarn build:dev, yarn test) to ensure code quality and build success.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided feature names to generate file paths and content. Ingestion points: feature-combo argument. Boundary markers: Absent. Capability inventory: File creation and modification, shell command execution via yarn. Sanitization: None specified. This represents a potential surface for indirect injection, but is evaluated as safe given the developer-focused use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM