encore-migrate
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill inventories all secrets and environment variables from the source codebase during the discovery phase. This is an intended feature to help migrate sensitive data to the target Encore environment but involves the agent handling plain-text credentials.
- [COMMAND_EXECUTION]: As part of the validation layer in the migration phase, the skill executes shell commands to run tests and verify the migrated code. The agent relies on these command outputs to mark units as successfully migrated.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary source code files from a user-provided directory, creating a vulnerability surface where instructions embedded in the source code could influence agent behavior.
- Ingestion points: All files within the source system path provided by the user (Phase 1, Section 2).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands within the source code data it reads.
- Capability inventory: The skill has the ability to read and write local files, execute shell commands (test suites), and make local HTTP requests for validation.
- Sanitization: There are no documented sanitization steps or filtering mechanisms for the content read from the source codebase.
Audit Metadata