slang-shader-engineer

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process and analyze external shader code, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to trigger on and process user-provided .slang files, shader code snippets, and C++ integration code as described in the SKILL.md and documentation references.
  • Boundary markers: The skill instructions lack explicit boundary markers or instructions to ignore potential commands embedded within the shader code it analyzes.
  • Capability inventory: The skill involves using the slangc CLI tool for compilation and providing C++ integration logic, which could be exploited if an attacker-controlled shader influences agent behavior (references/rules-and-patterns.md).
  • Sanitization: No sanitization or validation procedures are defined to ensure that the external code processed does not contain malicious instructions aimed at the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:12 AM
Security Audit — agent-trust-hub — slang-shader-engineer