reading-receipt

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local command-line utility named shinkoku to perform text extraction and image conversion on PDF documents.
  • [PROMPT_INJECTION]: As the skill parses text and images from external financial documents, it presents a surface for indirect prompt injection where embedded text could attempt to influence the agent's behavior.
  • Ingestion points: Data enters the context via the shinkoku pdf extract-text command and image processing through the vision-capable Read tool.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands when processing the extracted text.
  • Capability inventory: The skill can execute local CLI commands (shinkoku) and read file contents from the system.
  • Sanitization: There is no mention of sanitizing or validating the text extracted from documents before it is used to generate structured data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 05:14 AM