paper-search
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted academic data which introduces a risk of indirect prompt injection.
- Ingestion points: Content is retrieved from the web and academic repositories via web search and the arxiv_to_prompt tool.
- Boundary markers: The skill does not define specific delimiters to separate untrusted data from its instructions.
- Capability inventory: The skill uses arxiv_to_prompt and load_pdf to retrieve and display external documents.
- Sanitization: There is no mention of sanitizing or validating the text content retrieved from external sources.
Audit Metadata