autoglm-websearch

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill executes web searches via AutoGLM Web Search API and ingests external web page snippets/content into the agent's context.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The string 38d2391985e2369a5fb8227d8e6cd5e5 found in SKILL.md and websearch.py is a static application secret key/salt (APP_KEY) hardcoded into the script to generate MD5 request signatures for the AutoGLM Web Search API. This is a functional credential used for API authentication and signing, not a placeholder.