qms-audit-expert
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local Python script
scripts/audit_schedule_optimizer.pyused to calculate audit priorities and schedules. This is a legitimate functional component of the skill's auditing purpose. - [INDIRECT_PROMPT_INJECTION]: The
audit_schedule_optimizer.pyscript processes external data from a user-provided JSON file (--processes). This represents a potential surface for indirect prompt injection if the input data contains malicious instructions that are subsequently reflected in the script's output and processed by the agent. - Ingestion points:
scripts/audit_schedule_optimizer.pyreads data from a JSON file path provided via the--processescommand-line argument. - Boundary markers: None present in the script's text output to delineate untrusted data from instructions.
- Capability inventory: The script performs logic calculations and prints to stdout; it does not have network access, file-writing capabilities, or subprocess execution.
- Sanitization: No input sanitization or validation of the text content within the JSON fields is performed before outputting it to the agent's context.
Audit Metadata