mermaid-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill specifies saving files to a local directory (
00 收件箱/画板/mermaid流程图/). There are no network operations or attempts to access sensitive system files. - [Indirect Prompt Injection] (LOW): The skill processes arbitrary user-provided text to generate diagrams.
- Ingestion points: User-provided text or descriptions (SKILL.md, Step 1).
- Boundary markers: Absent; the instructions do not explicitly tell the agent to treat input as data only.
- Capability inventory: File writing (SKILL.md, Step 5).
- Sanitization: Absent; the agent is directed to extract logic directly from user input. This poses a low risk common to all LLM-based text processing skills.
- [No Code Execution] (SAFE): The skill consists entirely of markdown instructions and reference files. It does not contain any executable scripts (Python, JS, Shell) or binary files.
Audit Metadata