dev-builder
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process an external
Product-Spec.mdfile to drive its development tasks. This creates a surface for indirect prompt injection where malicious instructions inside a product document could attempt to influence the agent's behavior. - Ingestion points: The workflow explicitly reads
Product-Spec.mdin '步骤 1：读取产品文档' to determine features and priorities. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the product documentation.
- Capability inventory: The skill possesses the capability to write files, initialize projects via package managers (npm, pip, maven), and integrate with AI service APIs.
- Sanitization: There is no evidence of content sanitization or validation performed on the ingested product specification data.
Audit Metadata