grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill contains only natural language instructions and configuration. No executable scripts, binaries, or external dependencies were found in the provided files.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a workflow for analyzing user-supplied plans and designs, creating a potential data ingestion surface.\n
  • Ingestion points: User-provided design plans or project designs mentioned in the SKILL.md body.\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands were identified.\n
  • Capability inventory: No scripts or tools with file-writing, network, or execution capabilities were found in the provided context.\n
  • Sanitization: No explicit sanitization or validation of the input content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:17 AM
Security Audit — agent-trust-hub — grill-with-docs