Skills
skills/gnoviawan/agentic-marketing/marketing-social/Gen Agent Trust Hub

marketing-social

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill implements competitive research functionality that scrapes data from external social media platforms, creating an indirect prompt injection surface.
  • Ingestion points: The agent retrieves body text from Instagram, TikTok, and LinkedIn using the agent-browser tool (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from following instructions potentially embedded in the scraped website content.
  • Capability inventory: The skill utilizes browser automation and file write capabilities to save research results to the local filesystem (SKILL.md).
  • Sanitization: No sanitization or filtering logic for the scraped content is present in the skill's workflow.
  • [EXTERNAL_DOWNLOADS]: The skill installs and uses an external tool for browser-based research.
  • Fetches the agent-browser dependency from the Vercel Labs GitHub organization, which is a trusted and well-known source (SKILL.md, references/shared-patterns.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 01:13 AM