landing-page-design

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing additional components from the 'inference-sh' repository using the 'npx skills add' command.
  • [COMMAND_EXECUTION]: Utilizes the 'infsh' CLI tool via Bash to interact with remote AI models for image generation (falai/flux-dev-lora, bytedance/seedream-4-5) and web search (tavily/search-assistant, exa/answer).
  • [PROMPT_INJECTION]: Features an attack surface for indirect prompt injection via external data ingestion.
  • Ingestion points: Data is ingested from web search results provided by the Tavily and Exa tools.
  • Boundary markers: No explicit delimiters or 'ignore' instructions are provided to the agent for processing these search results.
  • Capability inventory: The skill allows execution of the 'infsh' command suite via Bash.
  • Sanitization: The skill does not implement specific sanitization or filtering of the content returned from search tools before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 12:06 PM