mj-markdown-formatter

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the skill instructions confirms they are limited to text processing and standard formatting tasks.\n- [SAFE]: No credentials, sensitive file paths, or exfiltration patterns were detected within the skill body or references.\n- [EXTERNAL_DOWNLOADS]: The README provides installation instructions for the 'skills' package from the author's own GitHub repository (makerjackie/skills), which is a standard distribution method and not an untrusted source.\n- [PROMPT_INJECTION]: No override attempts, role-play injections, or instructions to bypass safety guidelines were found. The prompt is strictly focused on formatting rules.\n- [SAFE]: The skill ingests user-supplied Markdown (Ingestion points: input text). Although it lacks explicit boundary markers, it has no capabilities that could be abused (Capability inventory: none), and sanitization is not required for its text-transformation purpose, making it safe against indirect prompt injection impacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 07:51 AM
Security Audit — agent-trust-hub — mj-markdown-formatter