db-migration-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze migration scripts provided by the user, which creates a surface for indirect prompt injection if those scripts contain malicious natural language instructions.\n
- Ingestion points: The workflow in SKILL.md requires the agent to request and process migration scripts.\n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the migration scripts.\n
- Capability inventory: The skill does not include any scripts, tools, or binary files that would allow for command execution, file system modification, or network access.\n
- Sanitization: No sanitization or validation logic is defined for the external input.\n- [NO_CODE]: The skill consists entirely of markdown instructions and configuration without any accompanying scripts, executables, or automated logic, significantly limiting its attack surface.
Audit Metadata