skills/zfinix/eleven/shader-check/Gen Agent Trust Hub

shader-check

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as GPU shaders, AIR (Apple Intermediate Representation), and performance recordings, which are potentially untrusted sources.
  • Ingestion points: GPU shaders, AIR code, and performance recording timelines (SKILL.md).
  • Boundary markers: There are no specific delimiters or instructions provided to the agent to help it ignore instructions that might be embedded in shader comments or metadata.
  • Capability inventory: The skill invokes the gpu_profile tool and reads file contents to generate optimization reports.
  • Sanitization: No sanitization or validation of the analyzed shader code is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 02:04 PM