mindmap-helper
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and structural templates. It does not include scripts, executables, or automated code workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided requirements, topics, and notes to generate hierarchical outlines. This creates an inherent surface for indirect prompt injection where instructions could be embedded in the source data.
- Ingestion points: User-supplied topics and requirements processed by the agent.
- Boundary markers: Absent; the skill does not define specific delimiters to wrap or isolate input data from instructions.
- Capability inventory: None; the skill's operations are limited to formatting text and generating JSON without calling external tools, writing to the file system, or performing network operations.
- Sanitization: Absent; the skill does not describe any methods for filtering or validating the content of the input requirements.
Audit Metadata