oma-pdf

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official installation script for the uv tool from astral.sh. It provides instructions for the agent to recommend a curl | sh command to the user if the required environment is not found.
  • [REMOTE_CODE_EXECUTION]: The skill dynamically downloads and executes Python packages (opendataloader-pdf, mdformat) from public registries using uvx. This is standard for its document processing workflow but involves runtime code execution.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its handling of untrusted input data.
  • Ingestion points: Ingests PDF files from the local filesystem specified by the user in input_path (SKILL.md).
  • Boundary markers: Extracted content is not enclosed in protective tags or markers to prevent the agent from following instructions embedded within the PDFs.
  • Capability inventory: The skill has the ability to execute shell commands and manage subprocesses via uvx (SKILL.md, resources/execution-protocol.md).
  • Sanitization: Content is normalized using mdformat, but no security-focused validation or escaping is performed on the extracted text before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 06:55 AM
Security Audit — agent-trust-hub — oma-pdf