mindmap-generator

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a potential indirect prompt injection surface (Category 8) as it processes user-provided mindmap data using high-privilege tools without explicit safety boundaries.
  • Ingestion points: User requests and mindmap generator patterns provided via natural language input (identified in SKILL.md).
  • Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore instructions embedded within the processed data.
  • Capability inventory: The skill's frontmatter configuration allows access to Read, Write, Edit, Bash(cmd:*), and Grep tools.
  • Sanitization: Absent; the instructions do not mandate validation, escaping, or filtering of external content before it is processed by the shell or file-writing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 04:28 PM
Security Audit — agent-trust-hub — mindmap-generator