paper-fetch
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The script generates suggested follow-up commands for batch failures. It uses
shlex.quoteto sanitize all user-controlled variables (DOIs and output paths), preventing command injection vulnerabilities. - [DATA_EXFILTRATION]: The skill performs outbound network requests to academic APIs and PDF repositories. It includes a robust SSRF (Server-Side Request Forgery) protection layer that validates URLs against private IP ranges, loopback addresses, non-standard ports, and cloud metadata endpoints.
- [EXTERNAL_DOWNLOADS]: The skill downloads content from external academic sources and mirrors. It enforces safety by validating the %PDF magic bytes of the response and strictly capping file sizes at 50MB to prevent resource exhaustion attacks.
- [PROMPT_INJECTION]: The skill instructions are focused on functional usage and do not contain patterns attempting to bypass agent safety filters or override system instructions.
Audit Metadata