fill-workday-timesheet

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill describes reading user-specific defaults from a local configuration file (~/.config/harness-configs/fill-workday-timesheet/config). This is a standard practice for managing local environment variables and does not involve arbitrary command execution from untrusted sources.
  • [DATA_EXFILTRATION]: No patterns of data exfiltration were detected. The skill interacts exclusively with the Workday application within the user's logged-in browser session and does not attempt to send information to external servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Workday web interface (such as current hours and lockout periods). To mitigate risks of the agent misinterpreting this data, the skill mandates a 'Phase 4' review where the proposed plan is presented to the user in a table, and execution is paused until the user explicitly accepts the plan.
  • [PROMPT_INJECTION]: The instructions are task-oriented and do not contain any language intended to bypass safety filters, override system instructions, or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 05:18 AM
Security Audit — agent-trust-hub — fill-workday-timesheet