skills/impertio-studio/mariadb-claude-skill-package/mariadb-agents-migration-validator/Gen Agent Trust Hub
mariadb-agents-migration-validator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted SQL dumps, schema files, and codebase contents, which creates an attack surface for indirect prompt injection. Malicious instructions could be embedded in SQL comments or string literals within the analyzed files.
- Ingestion points: User-supplied SQL dumps, database schemas, and application source code files (SKILL.md, references/methods.md).
- Boundary markers: Absent. The skill does not instruct the agent to use delimiters or warnings to separate data from instructions during analysis.
- Capability inventory: The skill is intended for high-capability agents (like Claude Code) that have access to file systems and shell environments.
- Sanitization: None present. The instructions do not describe any filtering or validation of the input content.
- [EXTERNAL_DOWNLOADS]: The skill references official MariaDB documentation for source verification and technical reference.
- Evidence: Links to
mariadb.com/docsandmariadb.com/kbare used to verify compatibility differences and index syntax.
Audit Metadata