site-architecture
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local files such as
.agents/product-marketing.mdor.claude/product-marketing.mdto gather business context. While this creates an ingestion point for external data, the skill lacks dangerous capabilities (like network operations or command execution) that could be exploited through this surface. - Ingestion points: The skill reads
product-marketing.md(and variations) from the local environment. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within these context files are provided.
- Capability inventory: The skill does not define any subprocess calls, file writes, or network operations.
- Sanitization: No explicit sanitization or validation of the ingested markdown content is performed.
Audit Metadata