support-staffing-model
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to generate calculations and an Excel report, which represents a managed data ingestion surface.
- Ingestion points: User-provided values for arrivals, handle time, and service levels are ingested via command-line arguments in
scripts/erlang_staffing.py. - Boundary markers: Input data is expected to conform to specific numeric and string formats defined in the script's argument parser.
- Capability inventory: The script performs file-writing operations using the standard
zipfilemodule to generate.xlsxoutput files. - Sanitization: The script uses
xml.sax.saxutils.escapeto sanitize all string inputs before they are embedded into the XML structure of the generated Excel document, mitigating risks associated with untrusted data interpolation.
Audit Metadata