qms-audit-expert
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local utility script,
scripts/audit_schedule_optimizer.py, which is used to generate risk-based audit schedules. The script is self-contained and uses standard Python libraries for date calculations and data processing. - [INDIRECT_PROMPT_INJECTION]: The audit scheduling script represents a surface for indirect prompt injection as it ingests process data from local JSON files provided by the user.
- Ingestion points:
scripts/audit_schedule_optimizer.pyreads data from a path specified by the--processesargument. - Boundary markers: Data is ingested as structured JSON; no specific "ignore instructions" markers are used within the data fields.
- Capability inventory: The script's functionality is limited to logic-based calculations; it contains no subprocess calls, file-system writes, network operations, or dynamic code execution (eval/exec) capabilities across its implementation.
- Sanitization: The script performs basic type validation and uses the standard Python
jsonlibrary for parsing input data.
Audit Metadata