legacy-modernizer
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process legacy codebases, which represent untrusted external data. There is a risk that malicious instructions hidden within comments or data structures of the legacy code could influence the agent's behavior during the refactoring process.
- Ingestion points: Legacy source code, framework configuration files, and database schemas as described in the 'Focus Areas' section of SKILL.md.
- Boundary markers: Absent. The instructions do not specify any delimiters (like XML tags or triple quotes) or explicit directives to ignore instructions found within the processed files.
- Capability inventory: The skill allows the agent to refactor code, generate test suites, create migration plans, and produce compatibility shims, providing a wide surface for potentially following instructions embedded in the input data.
- Sanitization: Absent. No logic is provided to filter, validate, or escape the content of the legacy code before the agent processes it.
Audit Metadata