project-roadmap-planning
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-provided content from specification files, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads project data from
specs/1_产品概述.mdandspecs/3_项目结构.md. - Boundary markers: The skill references an external file (
specs/GUARDRAILS.md) for safety rules but does not implement specific data delimiters in its workflow. - Capability inventory: The skill can scan directory structures (
docs/product_prototypes/,src/modules/) and write to local files (specs/6_开发路线图.md). - Sanitization: No explicit sanitization or validation of the input content is performed before it is used to generate the roadmap.
- Ingestion points: The skill reads project data from
- [COMMAND_EXECUTION]: The skill describes a progress detection workflow that involves scanning the local file system. This is a standard functional requirement for a project planning agent and does not involve the execution of arbitrary shell commands or privileged operations.
Audit Metadata