quality-manager-qms-iso13485
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data such as customer feedback, complaints, and audit results to perform QMS evaluations and generate reports. This creates a surface where malicious instructions could be embedded in the data to influence agent behavior. * Ingestion points:
SKILL.mdspecifies processing audit results, customer feedback, and product conformity data. * Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions in the processed data. * Capability inventory:SKILL.mdreferences the execution of several Python scripts for dashboarding and audit checklist generation (scripts/qms-performance-dashboard.py,scripts/audit-checklists/process-audit.py, etc.). * Sanitization: There are no instructions for sanitizing or validating external data before it is processed by the scripts or the agent. - [NO_CODE]: The skill references numerous functional scripts and reference documents that are not included in the provided package. The only provided script,
scripts/example.py, is a boilerplate placeholder with no functional logic.
Audit Metadata