gentic-influencer

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and guides the agent through a legitimate business workflow using established MCP tools (e.g., get_brand, search_creators).
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted external data.
  • Ingestion points: The fetch_page tool scrapes content from brand websites, and search_creators retrieves data from third-party social media platforms (Instagram and TikTok).
  • Boundary markers: There are no explicit instructions to the agent to disregard instructions embedded within the scraped web content or social media bios.
  • Capability inventory: The skill includes tools for web scraping, database storage, AI scoring, and generating export links.
  • Sanitization: The workflow does not specify sanitization or validation steps for content retrieved from external URLs or social media profiles.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 07:29 PM