dx-domain-discover
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository (identifiers, comments, and documentation) to generate a domain glossary. This analysis surface is inherent to its primary purpose.
- Ingestion points: The skill reads source code identifiers, module names, doc-comments, and existing project documentation (SKILL.md).
- Boundary markers: There are no explicit instructions to the agent to disregard instructions potentially embedded within the code being analyzed.
- Capability inventory: The skill uses
Exploresubagents to perform read operations across the repository and has write access tofoundation/glossary.md. - Sanitization: The skill enforces structural constraints by requiring the output to follow a specific glossary entry shape and limiting content to domain definitions, which provides a layer of defense against direct command reflection.
Audit Metadata