create-meta-prompts

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

• Third-party content exposure detected (high risk: 0.90). The skill's research patterns and execution instructions (e.g., references/research-patterns.md and research types) explicitly direct the agent to use WebSearch/WebFetch and external tools (e.g., GitHub, npm, Stripe docs, blogs, community sources) to fetch and ingest public web content—which are untrusted, user/third‑party sources—and to read/interpret those findings as part of its research/plan workflow.