33god-task-triage

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core workflow of processing untrusted external task descriptions.
  • Ingestion points: The skill ingests data from any user prompt describing a task or from the inbox workspace via the task.inbox.new event.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate user-provided task content from the agent's execution logic.
  • Capability inventory: The skill has the capability to write to the local filesystem (creating T0-subtasks.md) and perform external API calls to create developer stories on project boards.
  • Sanitization: There are no instructions to sanitize input or explicitly ignore potential instructions embedded within the task descriptions, allowing a malicious task description to potentially influence the agent's file-writing or ticket-creation behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 09:16 AM
Security Audit — agent-trust-hub — 33god-task-triage