Getting Started with Research Superpowers
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches scientific literature and metadata from PubMed E-utilities (
eutils.ncbi.nlm.nih.gov) and Semantic Scholar APIs (api.semanticscholar.org). These are well-known and trusted academic resources. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of paper abstracts and PDFs. While this represents an ingestion surface for indirect prompt injection, it is a necessary part of the skill's primary research function and is managed through structured workflows.
- [COMMAND_EXECUTION]: The skill references a local maintenance script,
./scripts/find-skills, used for discovering other research-related capabilities within the agent's environment.
Audit Metadata