octocode-researcher

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

• Third-party content exposure detected (high risk: 0.90). The skill's required GitHub/Package workflows (e.g., "The GitHub Flow" and tools like githubSearchCode, githubGetFileContent, packageSearch, and githubCloneRepo" in SKILL.md and references/fallbacks.md) instruct the agent to fetch and read public GitHub repositories and package metadata — untrusted third‑party, user-generated content — and to use those findings to drive follow-up actions and tool calls, creating a clear vector for indirect prompt injection.