trending-hub

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches hot search data from the vendor's API at https://redfox.hk. The connection logic in scripts/fetch_hotspot.py explicitly disables SSL certificate verification (ssl.CERT_NONE), which is a security best practice violation that could expose data to man-in-the-middle attacks.\n- [COMMAND_EXECUTION]: Executes the scripts/fetch_hotspot.py script to process trend data. The script uses the deprecated and insecure tempfile.mktemp() function to create temporary storage for JSON results, which is vulnerable to race conditions.\n- [DATA_EXFILTRATION]: Accesses the REDFOX_API_KEY environment variable for authentication with the vendor's API. This is the standard and recommended practice for secret management in this environment.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests untrusted external content.\n
  • Ingestion points: Hot search titles and URLs are fetched from external social platforms via the redfox.hk API in fetch_hotspot.py.\n
  • Boundary markers: Data is displayed within Markdown tables as defined in references/output-templates.md, but there are no explicit instructions for the agent to ignore or isolate instructions contained within the trend titles.\n
  • Capability inventory: The skill performs API requests and writes results to temporary local files; no high-risk capabilities like arbitrary shell execution or unsafe code evaluation were found.\n
  • Sanitization: The script performs formatting on heat counts but does not sanitize the content of trend titles before they enter the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:51 PM
Security Audit — agent-trust-hub — trending-hub