autoglm-websearch

Fail

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The script websearch.py contains a hardcoded secret key (APP_KEY = "38d2391985e2369a5fb8227d8e6cd5e5") used to generate MD5 signatures for API authentication.
  • [DATA_EXFILTRATION]: The skill initiates network requests to a local service at http://127.0.0.1:53699/get_token to fetch bearer tokens and sends search queries to the external ZhipuAI API endpoint at https://autoglm-api.zhipuai.cn/agentdr/v1/assistant/skills/web-search.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes 'snippet' and 'title' data from arbitrary third-party websites during the search process. This untrusted content is then presented to the agent, providing an attack surface for instructions embedded in web content to influence agent behavior.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 16, 2026, 06:01 PM