social-media

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The skill provides structural guidelines and platform-specific advice without any attempts to subvert the AI's core instructions.
  • Data Exposure & Exfiltration (SAFE): No sensitive file paths or credentials were found. File operations are restricted to local project directories for storing posts and research findings.
  • Indirect Prompt Injection (SAFE): The skill ingests data from a subagent (researcher) via research/[slug].md. While it lacks boundary markers and sanitization, its functional scope (writing content and generating images) does not provide a high-impact path for exploitation.
  • Execution Safety (SAFE): No remote code execution, package installation, or runtime code compilation patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:53 PM