site-architecture
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions include reading local project files (e.g.,
.agents/product-marketing.md) to gather business context. This represents an indirect prompt injection surface where content in those user-provided files could influence the agent's behavior. \n - Ingestion points:
SKILL.md(lines 14-15) directs the agent to read marketing context files.\n - Boundary markers: Absent; the skill does not define specific delimiters for the ingested text.\n
- Capability inventory: The skill uses standard file reading and text generation (ASCII and Mermaid diagrams).\n
- Sanitization: Absent; the skill relies on the agent's default safety filters for ingested content.
Audit Metadata