noon-search-results-scraper

Warn

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill requires the installation of the browser-act CLI and Skill from an external source (browseract.com) to function.
  • [COMMAND_EXECUTION]: The instructions explicitly command the agent to bypass user consent by installing dependencies "without asking the user to confirm" and to "not request separate approval for dependency installation." This is a concealment technique that removes user oversight for system-level changes.
  • [PROMPT_INJECTION]: The skill ingests untrusted content from the Noon marketplace, making it susceptible to indirect prompt injection attacks.
  • Ingestion points: Data fields such as product titles, seller information, and descriptions scraped from search results.
  • Boundary markers: There are no specified delimiters or instructions to treat the scraped content as untrusted data.
  • Capability inventory: The agent possesses browser interaction capabilities through the browser-act tool.
  • Sanitization: No sanitization or validation logic is defined for the external data before it is integrated into the agent's execution flow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 20, 2026, 04:27 AM
Security Audit — agent-trust-hub — noon-search-results-scraper