paper-to-intuition
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external academic papers which could potentially contain malicious or adversarial instructions intended to influence the agent's behavior during analysis.
- Ingestion points: The skill reads content from external sources including arXiv links, PDF files, and paper titles (SKILL.md).
- Boundary markers: The instructions do not include explicit delimiters or specific 'ignore embedded instructions' directives when processing the source paper content.
- Capability inventory: The skill generates structured markdown explanations and creates a self-contained HTML/JavaScript artifact for visual intuition diagrams.
- Sanitization: There are no specific instructions for sanitizing or escaping content from the papers before it is included in the generated explanations or the JavaScript-based visual artifact.
Audit Metadata