Project Management
Pass
Audited by Gen Agent Trust Hub on Jun 1, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill's instructions strictly focus on project management tasks such as task decomposition, sprint planning, and status reporting.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it imports and processes task data from external project trackers. -- Ingestion points: Project tracker APIs for Jira, Linear, GitHub Issues, and Trello are used to import backlog data. -- Boundary markers: Absent. The instructions do not define delimiters or specific constraints to prevent the agent from following instructions embedded within imported task descriptions. -- Capability inventory: The agent can perform write operations to tracker APIs and post messages to Slack and Teams channels. -- Sanitization: Absent. There is no mention of sanitizing or escaping imported content before processing.
Audit Metadata