Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted PDF data, creating a vulnerability surface for indirect prompt injection. 1. Ingestion points: PDF files processed via opendataloader-pdf. 2. Boundary markers: None identified in the provided file. 3. Capability inventory: Extraction of text, tables, and images from PDF to Markdown. 4. Sanitization: Not specified in the skill file.
- [SAFE]: No malicious command execution, hardcoded credentials, or obfuscation were detected in the analyzed file. The tool mentioned appears to be a legitimate data loading utility.
Audit Metadata