google-trends

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of playwright and chromium. These are well-known, trusted tools maintained by Microsoft for browser automation.
  • [COMMAND_EXECUTION]: The skill executes scripts/scraper.py, a bundled script that automates a browser to fetch trend data. This behavior is consistent with the skill's purpose.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes data from an external source (Google Trends).
  • Ingestion points: Data is fetched from trends.google.com internal APIs by scripts/scraper.py and saved as JSON.
  • Boundary markers: Absent; the instructions in SKILL.md do not specify delimiters to isolate the scraped content from the agent's instructions.
  • Capability inventory: The skill possesses the capability to execute a local Python script, write data to the filesystem, and perform network operations.
  • Sanitization: The script provides structural validation by stripping XSSI prefixes and parsing the captured content as JSON.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 12:17 PM
Security Audit — agent-trust-hub — google-trends