orval
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill defines workflows for processing external OpenAPI specifications which can serve as an injection vector for malicious instructions.\n
- Ingestion points: OpenAPI specification files or remote URLs processed as input targets in
references/orvalcfg-input-validation.md.\n - Boundary markers: Absent. The instructions do not provide delimiters or warnings to ignore embedded instructions within the specification.\n
- Capability inventory: The Orval generation process involves file system writes and potential command execution if build scripts are triggered.\n
- Sanitization: Absent. While input and output transformers are described in
references/adv-input-transformer.mdandreferences/adv-output-transformer.md, they focus on structural normalization rather than security validation.
Audit Metadata