medium-posts

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains only informational text and guidelines for the AI agent to follow when interacting with a user about Medium publishing. No executable scripts, binaries, or shell commands are included.
  • [DATA_EXPOSURE]: The skill instructs the agent to check for project context files (.claude/project-context.md or .cursor/project-context.md). This is a standard practice for AI agents operating within specific IDE environments to align output with project goals and does not involve accessing sensitive system files, environment variables, or credentials.
  • [PROMPT_INJECTION]: No malicious patterns, such as 'ignore previous instructions' or safety bypass attempts, were detected. The flow control instructions ('When invoking') are benign and intended for user experience optimization.
  • [NO_CODE]: The skill does not define any tools, dependencies, or remote code patterns. It operates entirely through natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 07:39 AM