ml-paper-writing

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow for citation management fetches external bibliographic text from outsider-authored public web APIs (e.g., Semantic Scholar/CrossRef/arXiv via HTTP requests) and may ingest that returned prose/metadata into the agent’s LLM context for drafting.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)