academic-paper-review
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's operational logic is strictly limited to academic document analysis and review generation. It does not perform unauthorized network requests, access sensitive local files, or execute shell commands.
- [PROMPT_INJECTION]: The skill is designed to process untrusted data from academic papers, which creates a potential surface for indirect prompt injection. This is a characteristic of the functionality rather than a specific vulnerability. Evidence: 1. Ingestion points: Academic paper URLs and uploaded PDF files. 2. Boundary markers: The instructions do not define specific delimiters for separating paper content from instructions. 3. Capability inventory: The skill uses file writing to sandbox paths and the file presentation tool. 4. Sanitization: No explicit sanitization of input text is defined.
Audit Metadata