ts2moonbit-migration
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze and port external TypeScript/JavaScript source code. This introduces a surface for indirect prompt injection, as malicious instructions could be embedded in the source code or comments of the files being processed.
- Ingestion points: Source code files (.ts, .js), declaration files (.d.ts), and existing test suites read during the migration process.
- Boundary markers: The skill does not define explicit delimiters to separate source code content from agent instructions, though it focuses on structural and type-level conversion.
- Capability inventory: The skill involves file-system operations (writing migrated code, building artifacts) and execution of shell commands (moon build, moon test, npm install).
- Sanitization: No specific sanitization or filtering of prompt-like content within the source files is prescribed.
- [EXTERNAL_DOWNLOADS]: The skill documentation and instructions include steps to fetch the skill and its required toolkit packages from external repositories and registries.
- Evidence: Mentions of apm install, moon add, and npx skills add for various mizchi toolkit packages.
Audit Metadata