yzr-sys-design-doc
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection because it processes untrusted data which could contain embedded instructions intended to manipulate the agent's output.
- Ingestion points: External data enters through user requirements in natural language and referenced code repository paths, as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to disregard potential commands found within the external input data.
- Capability inventory: The skill utilizes file system access to read source code and write generated Markdown documents (
<slug>-design.mdand<slug>-tasks.md), as specified in the 'Input and Output' section ofSKILL.md. - Sanitization: No filtering or sanitization procedures are implemented for the external content before it is processed by the agent.
Audit Metadata