site-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's instructions direct the agent to read and process external context files (such as .agents/product-marketing.md or .claude/product-marketing.md) to gather business and marketing background. This ingestion of untrusted data into the agent's context without explicit boundary markers or sanitization logic creates a surface for indirect prompt injection, where malicious instructions embedded in the data could attempt to influence the agent's behavior.
- Ingestion points: SKILL.md instructions to read marketing context files before planning.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore commands within the ingested context files.
- Capability inventory: The skill focuses on generating information architecture outputs (ASCII trees, Mermaid diagrams) but operates within an agent environment that typically includes tool access for file and shell operations.
- Sanitization: There are no specified steps for validating, filtering, or escaping the content retrieved from the external context files.
Audit Metadata