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
stophyandnpx @stophy/clicommands via theBashtool 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 (
stophyCLI) to perform web scraping and authentication. Access is limited to the vendor's specific toolset in the skill configuration.
Audit Metadata