skills/publora/skills/social-post/Gen Agent Trust Hub

social-post

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to the vendor's own infrastructure at mcp.publora.com and api.publora.com to perform its primary functions. These are expected communications for a service-integrated skill.
  • [COMMAND_EXECUTION]: The documentation includes standard setup commands for the Claude Code CLI (claude mcp add) to configure the Model Context Protocol (MCP) server. These commands are informational and use safe placeholders for authentication tokens.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as the create_post tool accepts arbitrary user-supplied text in the content parameter and processes external mediaUrls. However, this behavior is central to the skill's purpose of social media management, and the server-side validation described in the documentation provides a layer of protection against malformed inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:17 AM
Security Audit — agent-trust-hub — social-post