graph-engineering
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and does not include any executable scripts, shell commands, or tools that perform network communication or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to inform workflow design. (1) Ingestion: The skill reads conversation history, supplied artifacts, and context in SKILL.md. (2) Boundary: It enforces a strict 'Design-only boundary' that prohibits execution or system modification. (3) Capability: No subprocesses, exec/eval calls, file-write, or network operations are present. (4) Sanitization: Not explicitly performed. The strict design-only limitation contains the impact of any potentially malicious input.
Audit Metadata