code-visualizer

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing untrusted data from the local filesystem.
  • Ingestion points: The skill scans and reads the contents of Python source files (.py) and documentation files (such as README.md and ARCHITECTURE.md) using Path.read_text() and ast.parse to extract architectural metadata.
  • Boundary markers: The instructions lack explicit boundary markers or "ignore embedded instructions" warnings when processing these files, which could allow malicious instructions hidden in code comments or string literals to influence the agent's behavior.
  • Capability inventory: The skill possesses the capability to generate and maintain Markdown/Mermaid content and orchestrate tasks by invoking the mermaid-diagram-generator skill and the visualization-architect sub-agent.
  • Sanitization: There is no evidence of sanitization or filtering of the content extracted from the source files before it is used to generate diagrams or passed to downstream agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 09:49 AM