reading-receipt
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text from receipts and tax documents which could contain malicious instructions designed to manipulate the agent.
- Ingestion points: Data enters the context via the
shinkoku pdf extract-textcommand and vision-based image reading. - Boundary markers: The instructions do not define strict boundary markers or instructions to ignore embedded commands in the source documents.
- Capability inventory: The skill executes CLI commands and can invoke sub-agents for dual verification.
- Sanitization: There is no evidence of text sanitization or filtering applied to the extracted document content.
- [COMMAND_EXECUTION]: The skill executes external shell commands to process PDF files.
- Evidence: The skill uses
shinkoku pdf extract-text --file-path <path>andshinkoku pdf to-image --file-path <path> --output-dir <dir>to handle file conversions and data extraction.
Audit Metadata