cross-platform-campaign

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to a hosted MCP (Model Context Protocol) server at https://apikit.simplified.com/mcp to access social media management and image generation tools. This connection targets the official infrastructure for the Simplified platform.
  • [PROMPT_INJECTION]: The skill processes untrusted user-supplied marketing briefs to generate social media content, which constitutes an indirect prompt injection surface.
  • Ingestion points: The workflow in SKILL.md accepts user briefs, event announcements, and marketing requirements as the primary source for campaign generation.
  • Boundary markers: Explicit guardrails in SKILL.md mandate that all posts be created with an action: "draft" status and require human approval of the final campaign matrix.
  • Capability inventory: The skill utilizes tools to retrieve social media account identifiers (social_getSocialMediaAccounts) and create new post entries (social_createSocialMediaPost).
  • Sanitization: Content safety is managed through a 'stakeholder review package' and a multi-step approval workflow rather than automated filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:16 PM
Security Audit — agent-trust-hub — cross-platform-campaign