smart-folder-organizer

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion and processing of external document content.
  • Ingestion points: The skill extracts text from user-provided PDF files via the 'scripts/extract_pdf_metadata.py' script.
  • Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when presenting the extracted document text to the AI model for analysis.
  • Capability inventory: The agent has the authority to move and rename files across the target directory and its subdirectories based on the outcomes of its semantic reasoning.
  • Sanitization: No sanitization, filtering, or validation is performed on the extracted PDF content before it is passed to the AI model for classification.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 10:09 PM