ops-integrate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to prompt the user to paste an API key or credential in plain text, store it in a JSON preferences file, and use it directly in curl command-line arguments, exposing sensitive secrets within the LLM's context and execution environment.

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

• Third-party content exposure detected (low risk: 0.10). The workflow uses WebSearch to find API documentation for a given service name, which represents active fetching of web pages rather than automated consumption of unselected outsider feeds.