vs-octocode-research

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls public external sources (e.g., githubSearchCode and githubGetFileContent, and packageSearch as shown in SKILL.md and the README) and requires the agent to read and act on fetched public repository/package file contents and tool "hints" as part of its mandatory research workflow, so untrusted user-generated content can influence subsequent tool calls and decisions.