graph-schema
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of domain requirements, relational schemas, or existing graph models provided by the user to perform design and refactoring tasks. While this represents an ingestion surface for potential prompt injection, the skill lacks any dangerous capabilities (such as network access or file system writes) that could be leveraged for an attack.\n
- Ingestion points: User-provided domain requirements and schema definitions as defined in the skill scope in
SKILL.md.\n - Boundary markers: Absent.\n
- Capability inventory: None. The skill consists entirely of documentation and does not include any executable scripts, subprocess calls, or network operations across any files.\n
- Sanitization: Absent.\n- [NO_CODE]: The skill does not contain any executable code, binary files, or configuration for automated tools. All content is educational markdown documentation and Cypher query examples intended for human and AI instruction.
Audit Metadata