marketing-social

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and automates the installation of the agent-browser tool from the official Vercel Labs GitHub repository. This is a trusted organization and the download is documented neutrally as a functional requirement.
  • [COMMAND_EXECUTION]: The skill uses agent-browser commands to access public social media platforms (Instagram, TikTok, LinkedIn) for research purposes. These commands are scoped to gathering public information and are aligned with the skill's stated purpose.
  • [PROMPT_INJECTION]: While the skill ingests content from external websites via the browser tool (creating a potential surface for indirect prompt injection), it instructs the agent to prioritize local brand context and strategic guidelines, which acts as a mitigating boundary.
  • [SAFE]: No obfuscation, persistence mechanisms, or hardcoded credentials were found across the skill files and reference documentation. The skill follows standard local file organization practices for storing deliverables.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:57 AM