literature-review

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill’s workflow calls external literature databases/APIs (e.g., gget search pubmed, gget search biorxiv, Semantic Scholar/OpenAlex/Google Scholar scraping) and then aggregates exported results into markdown/PDF, so outsider-authored paper metadata/abstracts/full-text snippets fetched from public sources can be ingested into the agent’s LLM context.

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

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