site-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown and reference templates for website planning. No executable code, shell commands, or external network operations were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a data ingestion surface by instructing the agent to read context from
.agents/product-marketing-context.mdbefore proceeding with planning tasks. - Ingestion points:
SKILL.md(Check for product marketing context first section). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the skill instructions.
- Capability inventory: The skill is limited to text generation (ASCII trees) and visual diagram creation (Mermaid); it does not request or use file-write, network, or shell-execution tools.
- Sanitization: No sanitization of the external context data is defined.
Audit Metadata