map-architecture

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from the repository's source code to generate architecture documentation.
  • Ingestion points: The agent traverses the codebase to identify screens, interfaces, functions, and data flow patterns as described in Step 3 of the workflow.
  • Boundary markers: No specific delimiters or instructions are provided to the agent or its spawned sub-agents to ignore or treat codebase content as data rather than instructions.
  • Capability inventory: The skill is capable of writing multiple Markdown files to the filesystem (architecture/ directory) and can delegate tasks to up to three sub-agents, extending the execution context.
  • Sanitization: There are no mechanisms mentioned for sanitizing or escaping the content read from the codebase before it is incorporated into the agent's internal model or output artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:34 PM