email-sdk-migrate
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files to determine migration steps, which creates an attack surface where malicious instructions embedded in the scanned files could influence the agent's behavior during the edit process. 1. Ingestion points: The skill reads application source code, manifests, and lockfiles via the bundled audit script and direct inspection instructions. 2. Boundary markers: No specific delimiters or safety instructions are defined to isolate the content of the untrusted project files. 3. Capability inventory: The skill is authorized to read and modify project files and execute local CLI tools. 4. Sanitization: The ingested source code is not sanitized before being analyzed by the agent.
- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script (scripts/audit.mjs) and utilizes environment CLI tools like email-sdk doctor and email-sdk send to validate the migration process.
Audit Metadata