email-sdk-migrate
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions include a command to run a bundled Node.js script (
scripts/audit.mjs) to scan the user's project. This script only performs read-only filesystem operations and regex matching to identify legacy code patterns and does not execute any shell commands or external code. - [EXTERNAL_DOWNLOADS]: The skill references documentation and migration guides located at
https://email-sdk.dev/docs/guides/migrate. This is a vendor-owned resource used solely for instructional purposes by the agent. - [PROMPT_INJECTION]: The skill workflow involves reading and processing untrusted application source code, which represents an indirect prompt injection surface.
- Ingestion points: The
scripts/audit.mjsscript reads JavaScript, TypeScript, and Markdown files from the application root. TheSKILL.mdfile also instructs the agent to read manifest files and package source code. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the content of scanned files as untrusted data or to ignore embedded instructions.
- Capability inventory: The agent is empowered to perform file system modifications (updates to imports and construction logic) and execute validation tools like
email-sdk doctor. - Sanitization: There is no filtering or sanitization performed on the source code content before it is processed by the agent's context.
Audit Metadata