matlab-model-code-generator
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from various artifacts to drive its code generation process, creating a potential surface for instructions embedded in those files to influence agent behavior.
- Ingestion points: The agent is instructed to read logic from
methods/Qx/qx_method_candidates.mdandcode/model-code-analyzer.md, and process data fromworkspace/data/data_clean/. - Boundary markers: The workflow lacks instructions for the agent to use specific delimiters or guards when reading from these external documents.
- Capability inventory: The skill is designed to perform file system operations (write, mkdir) and generate executable MATLAB scripts based on the ingested content.
- Sanitization: No explicit input validation or sanitization process is defined for the content retrieved from the external method plans before it is incorporated into the generated code.
Audit Metadata