overseas-trending-search

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/digest.py uses subprocess.run to open the generated HTML report in a browser. The implementation uses a list of arguments without shell=True, which is a secure method for invoking system utilities.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the RedFox API (redfox.hk) to retrieve social media data. This activity is consistent with the skill's primary function and uses the vendor's own infrastructure.
  • [CREDENTIALS_UNSAFE]: The skill implements standard practices for API key management, supporting environment variables (REDFOX_API_KEY) and a local JSON configuration file (~/.qoder/apis/redfox.json), avoiding hardcoded secrets.
  • [PROMPT_INJECTION]: The skill processes untrusted content from social media platforms. The risk of indirect prompt injection is mitigated by storing data in a structured JSON format within the HTML report and applying HTML escaping (via textContent in report_template.html) before rendering. The ingestion points are the source-specific API responses, and capabilities include network requests, file writes, and browser execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 09:46 AM
Security Audit — agent-trust-hub — overseas-trending-search