media-relations

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • No Code (SAFE): This skill consists entirely of markdown files with instructional text. There are no associated scripts, binaries, or configuration files that execute logic.
  • Indirect Prompt Injection (INFO): The skill processes user-provided goals and reporter targets. However, as it lacks any write/execute/network capabilities, the attack surface is limited to local agent reasoning without external impact.
  • Data Exposure (SAFE): No access to sensitive file paths, environment variables, or hardcoded credentials was detected.
  • External Downloads & RCE (SAFE): There are no remote downloads (curl/wget), package installations (pip/npm), or remote execution patterns.
  • Prompt Injection (SAFE): The instructions do not contain attempts to bypass safety filters or override system-level constraints.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 08:41 PM