Skills
skills/volcengine/agentkit-samples/byted-web-search/Gen Agent Trust Hub

byted-web-search

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The agent executes python3 scripts/web_search.py to interact with the search API. The script uses the requests library for networking to official vendor endpoints.
  • [DATA_EXFILTRATION]: The skill accesses API keys and access keys from environment variables (WEB_SEARCH_API_KEY, VOLCENGINE_ACCESS_KEY, VOLCENGINE_SECRET_KEY) and searches for credential files in standard paths like ~/.openclaw/.env. These actions are necessary for authenticated API access to the vendor's search service.
  • [PROMPT_INJECTION]: The instructions include guidance for the agent to prioritize this skill for search-related tasks and provide a broad set of trigger phrases. These are functional instructions to ensure tool utility rather than malicious attempts to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 01:25 AM