volcengine-cli

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

• Third-party content exposure detected (low risk: 0.10). scripts/find_api.py fetches free-text fields (e.g., Search Highlight/Summary content) from an outsider-authored query result endpoint based on user/attacker-provided keywords, then prints/uses that returned text at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The Python helper scripts are invoked at runtime and fetch API definitions/search results from https://api.volcengine.com/api/common/explorer and https://api.volcengine.com/api/common/search/all?{params}, and those remote JSON responses are used to generate CLI parameter docs and drive command construction (i.e., they directly influence agent instructions), so this is a runtime external dependency that controls agent behavior.