Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to generate Python code and execute it using a shell-based sandbox to process PDF files. This is the core intended functionality of the skill.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data from PDF files.\n
- Ingestion points: The skill reads data from user-provided files such as
in.pdfandform.pdfusing libraries likepdfplumberandpypdf.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when handling extracted text.\n
- Capability inventory: The skill possesses file-writing capabilities and shell access within its sandbox environment.\n
- Sanitization: There is no evidence of sanitization or filtering of the content extracted from PDF files before it is returned to the agent context.
Audit Metadata