planning-jira-tasks
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses a modular architecture with specialized subagents and automated validation gates that verify artifact structure at every pipeline transition.
- [SAFE]: File access is restricted to reading and writing documentation artifacts in a designated workspace directory and loading local instruction templates.
- [PROMPT_INJECTION]: The skill processes Jira ticket descriptions which are untrusted external data. Ingestion points: docs/TICKET_KEY.md. Boundary markers: Enforced through structured task templates. Capability inventory: Restricted to local filesystem writes of markdown artifacts. Sanitization: Multi-stage structural validation ensures output adheres to expected formats.
- [SAFE]: No obfuscation, credential exposure, or remote code execution patterns were detected in the skill logic or its subagent definitions.
Audit Metadata