NYC

traffic-architect

Warn

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill directs the user or agent to install external plugins from an untrusted GitHub repository.
  • Evidence: In SKILL.md, the instructions recommend adding coreyhaines31/marketingskills via the command /plugin marketplace add coreyhaines31/marketingskills.
  • Risk: The account coreyhaines31 is not a trusted source. Suggested plugins could contain malicious code, telemetry, or exfiltration logic that would execute with the agent's permissions.
  • [NO_CODE] (SAFE): The skill itself contains no executable scripts or binaries. It consists entirely of Markdown guidance and JSON metadata.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:33 PM