temporal

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides templates for agents that ingest untrusted data from user signals and external activities, creating a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through signals in 'on_task_event_send' and via activities that perform web scraping (e.g., 'scrape_url' in 'activities.py').
  • Boundary markers: The provided examples lack clear delimiters or specific instructions to the agent to treat external content as data rather than instructions.
  • Capability inventory: The agents documented have access to network I/O (via 'httpx'), LLM interaction (via 'adk.providers.litellm'), and persistent state modification (via MongoDB).
  • Sanitization: The guide does not demonstrate input validation, filtering, or sanitization of content retrieved from external URLs before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 04:09 PM
Security Audit — agent-trust-hub — temporal