content-scheduler

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration downloads official MCP server packages, specifically @makenotion/mcp-server and @modelcontextprotocol/server-slack, from the public npm registry.
  • [COMMAND_EXECUTION]: The skill uses the npx command to run the Notion and Slack MCP servers. This is the standard method for initializing these integrations.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes content retrieved from external Notion databases.
  • Ingestion points: Notion database queries (SKILL.md)
  • Boundary markers: No explicit delimiters or warnings to ignore instructions within the retrieved content are implemented.
  • Capability inventory: The skill has the capability to write to Notion databases and post messages to Slack channels.
  • Sanitization: No explicit sanitization or filtering of the retrieved content is performed before it is handled by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:23 AM
Security Audit — agent-trust-hub — content-scheduler