sif-to-csv

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script located at <plugin-root>/skills/master-schedule/scripts/csv-library.py. This script is an internal vendor resource used to append processed data to the project's CSV library.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse data from external SIF files, which are provided by users or dealers. This represents an attack surface where maliciously crafted text inside SIF fields (such as Product Description or Specification Title) could attempt to influence the agent's behavior.
  • Ingestion points: External SIF files (e.g., dealer-quote.sif) or pasted text content containing dealer quote data provided by the user.
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" wrappers for the content parsed from the SIF file.
  • Capability inventory: The agent has access to Bash (to run the CSV helper), Write and Edit (to modify the product library), and Read (to access schema definitions).
  • Sanitization: The skill relies on an internal Python script (csv-library.py) to validate the data batch before performing an atomic replacement in the CSV library.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:03 PM