x-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly invokes xAI Grok's x_search to fetch and synthesize public X/Twitter posts and threads (see SKILL.md and the grok_search implementation in scripts/common.sh used by analyze.sh, digest.sh, search.sh), so it ingests untrusted, user‑generated third‑party content which directly informs analyses and suggested actions and could carry indirect prompt injections.