volcengine-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask users for AccessKey/SecretKey and authorization codes and to embed them verbatim into CLI commands (e.g., ve configure set --access-key <AK> --secret-key <SK> and scripts/ve_login_remote.sh complete <code>), which requires the LLM to handle and output secrets directly, creating a high exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime helper scripts (scripts/fetch_swagger.py and scripts/find_api.py) fetch live API data from Volcengine endpoints (e.g., https://api.volcengine.com/api/common/explorer and https://api.volcengine.com/api/common/search/all) and that fetched Swagger/search content is used at runtime to drive parameter discovery and command construction, i.e., external content directly affects agent prompts/instructions.