kadenzo-social-scheduling

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external social media platforms, creating a surface for indirect prompt injection.
  • Ingestion points: Content is retrieved from external sources via list_mentions, get_post, and list_posts (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific safety instructions to isolate or ignore potentially malicious commands within social media text.
  • Capability inventory: The skill includes tools for network interaction and content creation, specifically schedule_post, update_post, and post_comment (SKILL.md).
  • Sanitization: No filtering or sanitization of the retrieved social media content is specified before it is processed by the agent.
  • [SAFE]: The skill connects to official Kadenzo domains (kadenzo.app, studio.kadenzo.app) and uses the vendor's own MCP server for its core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 11:58 AM