deep-learning
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The README describes automated downloading of papers from URLs and academic repositories. Without the corresponding script, the security of these network operations cannot be assessed.
- COMMAND_EXECUTION (MEDIUM): The skill claims to run a local Python script with arguments. There is a risk of command injection if arguments are derived from untrusted web data without proper sanitization.
- PROMPT_INJECTION (LOW): The skill has a significant surface for Indirect Prompt Injection (Category 8). Ingestion points: Metadata, titles, and abstracts from external academic sources. Boundary markers: None documented. Capability inventory: Local script execution and file writing to the workspace. Sanitization: No evidence of sanitization for external content.
- NO_CODE (SAFE): The provided files are limited to Markdown documentation; the core functional logic and scripts are missing.
Audit Metadata