generate-connectivity-knowledge

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime LLM context can include outsider-authored free text from public web content fetched at runtime during Step 2 (WebFetch/WebSearch of documentation URLs) and Step 9 (Deep Research WebFetch/WebSearch), which the agent reads and uses to generate/validate schemas and specs.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly WebFetches documentation and prioritizes machine-readable OpenAPI specs which are fetched at runtime and used as authoritative inputs to drive spec generation and validation (e.g., the example OpenAPI URL https://developer.atlassian.com/cloud/jira/platform/swagger-v3.v3.json), so remote content can directly control the agent's behavior and is a required runtime dependency.