academic-research
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The entire skill suite consists of documentation, instructional guides, and document templates. No Python or Node.js packages are included, and there are no shell scripts or automated commands that could compromise the host environment.
- [PROMPT_INJECTION]: The skill suite includes sub-skills for reading papers and analyzing professor profiles, which involve ingesting untrusted external data from PDFs, arXiv URLs, and web pages. This represents a potential surface for indirect prompt injection. However, this is an inherent and intended part of the research functionality, and no evidence of malicious intent or hidden prompt overrides was detected. Ingestion points: paper-reading/SKILL.md and professor-fit-analyser/SKILL.md. Boundary markers: Absent. Capability inventory: Web browsing and file reading. Sanitization: Absent.
Audit Metadata