tiktok-keyword-user-search

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The scripts scripts/search_user.py and scripts/fetch_user_following.py attempt to locate the REDFOX_API_KEY by reading the user's shell configuration files (e.g., ~/.zshrc, ~/.bashrc) if the key is not found in the environment variables or command-line arguments. This is a targeted search for the skill's specific API key intended to improve user experience.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill performs network requests to the vendor's API at https://redfox.hk. It uses a custom SSL configuration (disabling SNI and hostname verification) which is documented as a requirement for compatibility with the vendor's specific network infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from TikTok. To protect the agent's context from malformed data or potential injection, the scripts include an escape_md function that sanitizes strings (such as usernames and signatures) before they are displayed in Markdown tables.
  • [REMOTE_CODE_EXECUTION]: The skill does not have any external dependencies and only utilizes Python's standard library, which reduces the potential for supply chain attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 11:38 PM