a2ui-migration
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted repository content, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent is directed to read manifest files (package.json, pubspec.yaml, pyproject.toml), source code, fixtures, goldens, and prompts stored in the user's repository (SKILL.md).
- Boundary markers: The skill does not provide specific instructions to use delimiters or warnings to separate this external data from the agent's instructions.
- Capability inventory: The instructions guide the agent to perform file system modifications, dependency resolution, and test execution (SKILL.md).
- Sanitization: No explicit sanitization or validation of the ingested file content is mentioned.
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard development tools, including compilers, analyzers, type checkers, and test runners to verify the migration (SKILL.md). These are legitimate operations within the scope of software development and migration.
Audit Metadata