review-sql
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's logic is entirely contained within Markdown and YAML instruction files. It does not include any scripts, binaries, or configuration that would execute on a host system.
- [NO_CODE]: No external dependencies, package manifests, or remote code execution patterns were detected in the skill files.
- [PROMPT_INJECTION]: The skill processes user-provided SQL code, which creates an indirect prompt injection surface (Category 8). However, the skill has no dangerous capabilities to exploit.
- Ingestion points: Input 'code-scope' containing SQL code defined in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters to separate user data from instructions.
- Capability inventory: No subprocess, network, or file-write operations are defined in any file.
- Sanitization: No explicit sanitization or validation of the input SQL content is described.
Audit Metadata