beautiful-mermaid
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions advise installing
beautiful-mermaid-clivia NPM or a Homebrew tap (okooo5km/tap/bm). These resources are provided by the skill author and are required for functionality. - [COMMAND_EXECUTION]: The skill operates by executing the
bmCLI tool, which takes user-supplied Mermaid code and various configuration flags as arguments. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted input (Mermaid diagrams) which could be used to influence the agent or escape command boundaries.
- Ingestion points: Mermaid source code is ingested via the
-cflag or through file paths specified inSKILL.mdandreference.md. - Boundary markers: None. The instructions do not provide delimiters or warnings to ignore instructions within the Mermaid source.
- Capability inventory: The
bmtool can execute shell commands, read from the file system, and write output files. - Sanitization: None. There are no instructions for validating or sanitizing the Mermaid code before it is passed to the shell command.
Audit Metadata