stophy-real-estate

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from external platforms like Zillow and Realtor.com, which introduces a surface for untrusted data to potentially influence the agent's behavior.
  • Ingestion points: The skill scrape real estate listings and property details from Zillow and Realtor.com URLs as outlined in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential instructions embedded in the scraped web content.
  • Capability inventory: The agent is permitted to execute stophy and npx @stophy/cli commands via the Bash tool to retrieve data.
  • Sanitization: No sanitization, filtering, or validation steps for the external data are described in the instructions.
  • [COMMAND_EXECUTION]: The skill directs the agent to interact with a command-line interface (stophy CLI) to perform web scraping and authentication. Access is limited to the vendor's specific toolset in the skill configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:19 PM