legacy-migration-planner
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves ingesting and processing a user's entire codebase, which creates a large attack surface for instructions embedded in source code or metadata.
- Ingestion points: Step 1 (references/research-phase.md) directs the agent to analyze project structures, entry points, configuration files, and all source modules.
- Boundary markers: The skill does not provide instructions to distinguish between passive data and active instructions within the analyzed codebase, nor does it include 'ignore' rules for embedded content.
- Capability inventory: The agent has the ability to perform web searches, access internal library documentation via the context7 tool, and write multiple planning files to the file system (SKILL.md).
- Sanitization: No sanitization, validation, or escaping protocols are defined for the data extracted from the analyzed files before it is processed by the agent.
Audit Metadata