to-tickets
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions include steps to explore the codebase and fetch external references (spec paths, issue URLs) to understand project context. These operations are essential for the primary functionality of drafting project tickets.
- [DATA_EXFILTRATION]: The skill publishes approved tickets to external issue trackers such as GitHub or Linear. This behavior is documented, requires prior setup through a specific configuration command, and only occurs after the user approves the drafted plan.
- [PROMPT_INJECTION]: There is an inherent surface for indirect prompt injection because the skill ingests content from external URLs and local specifications.
- Ingestion points: Conversation context, local file paths for specifications, and remote issue URLs.
- Boundary markers: The skill uses a structured vertical-slice rule set but does not use specific markers to delineate untrusted data from instructions.
- Capability inventory: File reading, codebase exploration, and publishing to issue trackers via configured tools.
- Sanitization: No explicit sanitization of input data is mentioned, but the process includes a mandatory "Quiz the user" step which acts as a human-in-the-loop review mechanism before execution.
Audit Metadata