ai-feature-prd
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and markdown templates. It does not contain any executable scripts, shell commands, or external code dependencies.
- [SAFE]: The skill's operations are limited to reading from and writing to local workspace files within a predefined structure (e.g.,
entities/,decisions/, andprofessional-braindirectories). There are no network operations, hardcoded credentials, or attempts to access sensitive system files. - [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to bypass safety filters, ignore previous instructions, or extract system prompts. The language is purely instructional for the purpose of PRD generation.
- [DATA_EXFILTRATION]: No network tools or external data transfer mechanisms are utilized. Data remains within the local environment provided to the agent.
Audit Metadata