generate-mindmap
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for static data processing and visualization. It contains no instructions for external network access, credential harvesting, or system modification.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text content to generate mindmaps, creating a surface for potential instruction injection through processed data. 1. Ingestion points: User-provided text content (SKILL.md). 2. Boundary markers: None mentioned. 3. Capability inventory: The skill only has the capability to write a JSON file to local storage at /tmp/mindmap-outline.json (SKILL.md) and does not possess network or command-execution tools. 4. Sanitization: No explicit sanitization is performed, however, the structural constraints of the 'Rule of One' (limiting nodes to single keywords) and the specific JSON schema requirements act as effective natural barriers against complex malicious instruction payloads.
Audit Metadata