asyncapi-design

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: Data is retrieved from external sources using mcp__perplexity__search and mcp__context7__query-docs.
  • Boundary markers: The instructions lack delimiters or warnings to treat external tool outputs as untrusted content.
  • Capability inventory: The skill is permitted to use Write and Edit tools, which allows for local file modification based on external input.
  • Sanitization: No input validation or sanitization processes are defined for retrieved data.
  • [NO_CODE]: The skill consists of markdown documentation and reference templates without any accompanying executable scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 09:01 AM