ddd-scope
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a template for business requirement analysis. It does not include any executable code, command-line operations, or tool invocations. The agent logic is limited to reasoning and text generation based on user-provided descriptions.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection because it is designed to ingest and process unstructured external data such as PRD excerpts, verbal notes, and ticket descriptions. While this allows for the ingestion of malicious instructions, the skill lacks the capabilities (such as network access or shell execution) required to exploit such an injection. The risk level is negligible and consistent with standard requirement analysis tools.
- Ingestion points: Processes business objectives, PRD fragments, and ticket descriptions in the input requirements section of SKILL.md and SKILL.en.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
- Capability inventory: No tools, shell commands, or network operations are requested or used.
- Sanitization: No input validation or filtering logic is implemented.
Audit Metadata