oracle-domain-modelling
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted data from the project's source code and documentation.
- Ingestion points: Reads file content from
CONTEXT.md,CONTEXT-MAP.md,docs/adr/, andsrc/directories. - Boundary markers: No delimiters or specific instructions are provided to distinguish between project data and agent instructions.
- Capability inventory: The skill is capable of reading and writing files within the project repository.
- Sanitization: No sanitization or validation of the ingested file content is performed.
Audit Metadata