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
uvtool fromastral.sh. It provides instructions for the agent to recommend acurl | shcommand 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 usinguvx. 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