mind-map-generator
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text (story outlines, character lists) to generate mind maps. This presents an indirect prompt injection surface if the input contains malicious instructions designed to influence the agent's behavior during the conversion process.
- Ingestion points: The
contentparameter inMindMapGenerator.generate_mind_map(scripts/mind_map_generator.py) accepts arbitrary text input from the user. - Boundary markers: The skill instructions in
SKILL.mdspecify a strict output JSON schema and constrain the agent from introducing information unrelated to the mind map generation. - Capability inventory: The associated script performs local string manipulation and regex-based parsing only. It has no network, file-write, or shell execution capabilities.
- Sanitization: The script uses regex to extract structural elements but does not explicitly sanitize the text content for LLM instructions. However, the logic is purely data-transformative, limiting the impact of any injected text.
Audit Metadata