semantic-paper-radar
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill describes workflows for processing and synthesizing information from external academic paper abstracts. This ingestion of untrusted data presents a surface for indirect prompt injection, as the provided instruction templates lack explicit boundary markers or sanitization steps.
- [EXTERNAL_DOWNLOADS]: Mentions the use of standard Python packages including
chromadbandsentence_transformers, and references the SPECTER2 model from the Allen Institute for AI. - [COMMAND_EXECUTION]: Includes examples of using
curlto query the OpenAlex API for retrieving research paper metadata.
Audit Metadata