skills/dev-goraebap/skills/make-erd/Gen Agent Trust Hub

make-erd

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external sources such as PRDs and requirement definitions to generate diagrams.
  • Ingestion points: Data enters the agent context through user prompts or uploaded files in formats like .md, .pdf, .txt, and .mmd (SKILL.md, README.md).
  • Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from obeying instructions that might be embedded within the processed documentation.
  • Capability inventory: The skill's primary capabilities include creating directories and writing Mermaid (.mmd) files to the local file system (SKILL.md).
  • Sanitization: There is no evidence of input validation or sanitization routines to filter out malicious instructions from the source documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 11:29 AM
Security Audit — agent-trust-hub — make-erd