qlik-ai-readiness-optimizer
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Qlik applications which could potentially contain malicious instructions.
- Ingestion points: Untrusted data is retrieved from the target application via tools including
qlik_describe_app,qlik_get_fields,qlik_list_measures, andqlik_list_dimensions(SKILL.md, Phase 1 and 2). - Boundary markers: The skill instructions do not define specific delimiters or isolation techniques (e.g., XML tags or clear separators) to distinguish between instructions and ingested data.
- Capability inventory: The skill has the capability to perform write operations in the Qlik environment using tools such as
qlik_create_measure,qlik_update_measure,qlik_create_dimension, andqlik_update_dimension(references/implementation-guide.md). - Sanitization: No explicit logic is provided for sanitizing or filtering input retrieved from the Qlik application before it is processed by the model or presented to the user.
- Mitigation: The risk is mitigated by a mandatory 'Human-in-the-Loop' confirmation step (SKILL.md, Phase 4) and Key Rule #8, which requires user approval before any implementation steps are executed.
Audit Metadata