tighten-prose

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches live pattern data from Wikipedia via an API call, which exposes the agent to outsider-edited web content at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to make a live HTTP call to Wikipedia at runtime to fetch pattern updates, forming an operational dependency on an external URL.