mermaid-validate

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs the Bash tool to perform recursive file searches with find, run dependency setup scripts, and execute syntax validation logic via Node.js scripts distributed with the skill.\n- [EXTERNAL_DOWNLOADS]: Includes a process to ensure dependencies, which typically involves downloading software packages from standard package registries (like npm or pip) to ensure the validation scripts function correctly.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external markdown files which may contain untrusted content.\n
  • Ingestion points: Markdown files provided by the user via the path argument and identified in SKILL.md (Step 3 and 5).\n
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or specific warnings to ignore instructions embedded within the processed markdown content.\n
  • Capability inventory: Use of Bash and Node.js to execute scripts and system commands based on user-supplied file paths (SKILL.md, Step 1, 2, and 5).\n
  • Sanitization: Absent; the instructions do not specify any validation or sanitization of the markdown file content before it is passed to the extraction and validation scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:28 PM
Security Audit — agent-trust-hub — mermaid-validate