te2-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and using external public artifacts (e.g., the BPA rules URL https://raw.githubusercontent.com/.../BPARules.json and the guidance to use microsoft_docs_search + microsoft_docs_fetch or mslearn fetch) so the agent will ingest untrusted, user-hosted web content as part of its workflow, which can materially influence analysis and subsequent tool actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The "Run BPA Analysis" example shows TabularEditor.exe invoked at runtime with a raw GitHub URL (https://raw.githubusercontent.com/microsoft/Analysis-Services/master/BestPracticeRules/BPARules.json), which the CLI will fetch and use as BPA rule instructions that directly control the tool's analysis behavior.