wechat-draft-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires and digests external "reference materials (links, notes, reports, docs)" as a required input and instructs the agent to "Digest source material" and "Keep factual claims anchored to provided references" (see SKILL.md Workflow steps 1 and 5 and references/draft-dna-enforcement.md Required Inputs), which means it will read and act on untrusted third‑party content that could carry injected instructions.