skills/xenodium/emacs-skills/mermaid/Gen Agent Trust Hub

mermaid

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes emacsclient to retrieve the foreground color and background mode from the host Emacs environment.
  • [COMMAND_EXECUTION]: The skill runs the mmdc (Mermaid CLI) tool via Bash to transform Mermaid text into PNG images, using a specified local Chromium path for the Puppeteer backend.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the conversation context to generate diagrams.
  • Ingestion points: Diagram content is derived from the most recent interaction context (SKILL.md).
  • Boundary markers: Absent; the skill does not wrap the context data in protective delimiters or provide instructions to ignore embedded commands.
  • Capability inventory: The skill uses the Bash tool to execute emacsclient and mmdc and can write temporary files to /tmp (SKILL.md).
  • Sanitization: Absent; extracted context data is written directly to a temporary file and passed to the Mermaid renderer without validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:51 PM