to-tickets

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows a standard workflow for project management and task decomposition. It gathers information from the conversation context and codebase to create vertical slices of work.
  • [EXTERNAL_DOWNLOADS]: The skill instructions include fetching content from external references such as issue numbers or URLs (e.g., GitHub or Linear). This is a functional requirement for ticket creation and triage tasks and uses standard service integrations.
  • [DATA_EXPOSURE]: The skill reads the local codebase to understand domain glossary and architecture. This access is scoped to providing relevant ticket descriptions and does not involve exfiltration to unauthorized endpoints.
  • [PROMPT_INJECTION]: As the skill processes untrusted data from external URLs and specs, it is theoretically susceptible to Indirect Prompt Injection (Category 8). However, the skill includes a mandatory human-in-the-loop step (Step 4: Quiz the user) where the agent must present the proposed breakdown for approval before publishing, significantly mitigating the risk of executing injected instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:26 PM
Security Audit — agent-trust-hub — to-tickets