reports-morning-briefing
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill instructions are focused on retrieving and summarizing personal productivity data for the user.
- [DATA_EXFILTRATION]: While the skill accesses multiple data sources (Slack, Email, Calendar, Jira), it does so using authorized tools to present a summary back to the user. There are no patterns suggesting data is being sent to external or unauthorized servers.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess calls, or dynamic code execution triggers. It strictly uses defined tool APIs for information retrieval.
- [PROMPT_INJECTION]: No evidence of instructions designed to bypass agent constraints or safety filters. The skill processes external data (emails, messages) but explicitly constrains its output to a read-only summary format, preventing the execution of any instructions contained within that data.
- [DYNAMIC_EXECUTION]: No use of runtime code generation, compilation, or unsafe deserialization.
Audit Metadata