asana-automation

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill calls Asana API endpoints (e.g., ASANA_SEARCH_TASKS_IN_WORKSPACE, ASANA_GET_A_TASK, ASANA_GET_WORKSPACE_PROJECTS) to read task names/notes, project data, and user content — which are user-generated third‑party contents the agent will ingest and could contain injected instructions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires a live Rube MCP connection and explicitly instructs adding and using https://rube.app/mcp (via RUBE_SEARCH_TOOLS) at runtime to fetch current tool schemas, meaning content from that URL can directly control the agent's prompts/instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:23 PM