components-breadcrumb
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a static reference for breadcrumb implementation, providing HTML, JSON-LD, and Next.js templates.
- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill instructs the agent to read local context files (.claude/product-marketing-context.md and .cursor/product-marketing-context.md). 1. Ingestion points: Instructions in the 'Initial Assessment' section for reading external marketing context files. 2. Boundary markers: Absent. 3. Capability inventory: None. The skill only outputs text and code snippets; it does not perform subprocess calls, file writes, or network requests. 4. Sanitization: Absent.
Audit Metadata