sutochno

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the patchright Python package and utilizes a Docker base image (ghcr.io/borski/patchright-docker) maintained by the author. These resources are used to provide the browser environment required for scraping.
  • [COMMAND_EXECUTION]: The script launches a Chromium browser process through the Patchright library to navigate to and extract data from Sutochno.ru city subdomains.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted text from a third-party website.
  • Ingestion points: Listing titles, addresses, and price strings are extracted from the DOM of Sutochno.ru pages in scripts/search_sutochno.py.
  • Boundary markers: The skill does not currently use specific delimiters or instructions to the agent to ignore potentially malicious content within the scraped strings.
  • Capability inventory: The skill uses a browser to perform network requests and returns external data to the agent's context.
  • Sanitization: Content undergoes basic whitespace normalization but is otherwise processed as raw strings before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 04:40 PM
Security Audit — agent-trust-hub — sutochno