office-pdf
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
mkdir,cp,uv run) to prepare a working directory and execute Python-based PDF parsing scripts. These commands are used for environment setup and task execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes external PDF files provided at runtime to extract text or tables. This creates a surface where malicious instructions embedded in a PDF could influence the agent's behavior.
- Ingestion points: External PDF files processed via
pdfplumberandpypdfas described inSKILL.md. - Boundary markers: None identified; extracted text is printed directly to standard output.
- Capability inventory: The skill uses shell commands and
uv runto execute Python code, which can perform filesystem operations within thework/directory. - Sanitization: No explicit sanitization or filtering of the extracted text is performed before it is processed by the agent.
Audit Metadata