qlik-ai-readiness-optimizer
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata from Qlik applications, which serves as an ingestion point for potential indirect prompt injection attacks.
- Ingestion points: Metadata is retrieved from the target application via
qlik_get_fields,qlik_list_measures,qlik_list_dimensions, andqlik_get_full_glossary_exportduring the analysis phase. - Boundary markers: The skill does not explicitly instruct the agent to use boundary markers or delimiters when processing the external application data.
- Capability inventory: The agent possesses write capabilities to the Qlik environment through tools such as
qlik_create_measure,qlik_update_measure,qlik_create_dimension,qlik_update_dimension,qlik_create_glossary_term_links, andqlik_update_glossary_term. - Sanitization: There are no specific instructions for sanitizing or filtering the metadata retrieved from the application before processing.
- Mitigation: The potential risk is effectively managed by a strict "Human-in-the-Loop" requirement, where all findings and proposed optimizations must be presented to and approved by the user before implementation.
Audit Metadata