obsidian-file-intel

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process content from various untrusted file formats (PDF, PPTX, XLSX, DOCX, CSV, JSON, XML, MD, TXT, PY, JS, HTML, CSS). This creates a significant surface for indirect prompt injection attacks.
  • Ingestion points: The scripts/process_files_with_gemini.py script reads and extracts data from files in a user-provided directory.
  • Boundary markers: The instructions do not specify any delimiters or warnings to the model to ignore instructions embedded within the processed file content.
  • Capability inventory: The skill utilizes shell execution (python, open) to process data and display results.
  • Sanitization: There is no evidence of sanitization or filtering applied to the content of the files before they are processed by the LLM.
  • [COMMAND_EXECUTION]: The skill executes shell commands using user-supplied directory paths: python scripts/process_files_with_gemini.py <folder_path>. This pattern is susceptible to command injection if the agent does not properly escape or validate the <folder_path> input before passing it to the bash environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:05 PM
Security Audit — agent-trust-hub — obsidian-file-intel