asana-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from Asana.
  • Ingestion points: Tools such as ASANA_GET_A_TASK, ASANA_GET_TASKS_FROM_A_PROJECT, and ASANA_SEARCH_TASKS_IN_WORKSPACE retrieve user-controlled content like task names and notes.
  • Boundary markers: Absent. The instructions do not provide delimiters or specific guidelines for the agent to distinguish between its instructions and the data retrieved from Asana.
  • Capability inventory: The skill has significant write/delete capabilities, including ASANA_CREATE_A_TASK, ASANA_SUBMIT_PARALLEL_REQUESTS (bulk operations), and various project management tools.
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from the Asana API.
  • [SAFE]: The skill uses RUBE_MANAGE_CONNECTIONS for authentication. This is a secure practice that relies on OAuth rather than hardcoded API keys or secrets.
  • [SAFE]: The skill references rube.app and composio.dev. These are established services in the AI agent ecosystem for providing toolkits and MCP infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — asana-automation