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
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:35 PM