segment-automation

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to configure an external MCP server at https://rube.app/mcp. This remote service provides the Segment tool implementations required for the automation workflows described in the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection through its data ingestion tools. 1. Ingestion points: User-provided properties and traits in tools like SEGMENT_TRACK, SEGMENT_IDENTIFY, and SEGMENT_BATCH. 2. Boundary markers: None present; the skill does not instruct the agent to use delimiters or ignore embedded instructions within the properties or traits data. 3. Capability inventory: The skill uses tools to write data to the external Segment API (SEGMENT_TRACK, SEGMENT_IDENTIFY, SEGMENT_BATCH, SEGMENT_GROUP, SEGMENT_PAGE, SEGMENT_ALIAS). 4. Sanitization: The skill provides a manual pitfall warning regarding PII but does not implement or instruct on technical sanitization or escaping for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:49 PM