quality-manager-qms-iso13485
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted external data which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: As outlined in
SKILL.md, the skill is designed to ingest and analyze external content including 'Audit results (internal and external)', 'Customer feedback and complaints', and 'Process performance' metrics. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers (e.g., XML tags or clear separators) to isolate external data from the primary instruction set.
- Capability inventory: The skill references automation scripts for QMS performance tracking and document control verification (e.g.,
scripts/qms-performance-dashboard.py), which would process the external data mentioned. - Sanitization: There are no mentioned mechanisms for sanitizing, validating, or filtering external text before it is processed by the AI agent.
Audit Metadata