search-intent-coverage

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Unverifiable Dependencies (MEDIUM): The skill instructs the installation of the 'agent-browser' npm package globally. This package is not hosted in a trusted repository or organization defined in the security guidelines.
  • Dynamic Execution (LOW): The skill relies on executing CLI commands through 'agent-browser' to interact with live web pages. While typical for scraping, this introduces a surface for command-line interaction with external tools.
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from the web (SERP results and competitor pages) to build its output.
  • Ingestion points: Competitor page text and structure extracted via 'agent-browser get text' and 'snapshot'.
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore instructions contained within the scraped text.
  • Capability inventory: Shell command execution (agent-browser) and SERP API interactions.
  • Sanitization: Absent. Content is processed directly to identify patterns and headings.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:10 PM