skills/wh-2099/mermaid-skill/mermaid/Gen Agent Trust Hub

mermaid

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-supplied diagram descriptions, which represents an ingestion surface for untrusted content. \n
  • Ingestion points: User requirements enter the agent context through the $ARGUMENTS variable in SKILL.md. \n
  • Boundary markers: Absent. The prompt does not utilize explicit delimiters to encapsulate the user-provided requirement text. \n
  • Capability inventory: The skill allows access to Read, Write, and Edit tools as defined in the frontmatter of SKILL.md. \n
  • Sanitization: Absent. There is no automated filtering or sanitization of the requirement string before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 09:06 PM
Security Audit — agent-trust-hub — mermaid