search-papers
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration, or obfuscation detected. The skill performs a legitimate task of academic literature search.
- [INDIRECT_PROMPT_INJECTION]: The skill processes abstracts and titles from external academic databases (arXiv, Semantic Scholar). This represents a theoretical indirect prompt injection surface if paper metadata were to contain malicious instructions. However, the risk is inherent to any data-retrieval task and is mitigated by the skill's instruction to summarize the content into a specific structured format.
Audit Metadata