skills/ninehills/skills/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingest user-provided plans and designs which could potentially contain embedded instructions.
  • Ingestion points: Processes user-supplied designs and plans.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
  • Capability inventory: The skill is instructed to 'explore the codebase', implying read access to local files.
  • Sanitization: No explicit sanitization or validation of the input content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 06:42 AM
Security Audit — agent-trust-hub — grilling