eisenhower-priority-ai
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted task lists provided in the input context and incorporates them into the final output artifacts.\n
- Ingestion points: The
input.context.tasksobject insrc/index.jsis used to populate markdown tables and action plans.\n - Boundary markers: Absent; the task data is interpolated directly into the markdown output without delimiters or system-level instructions to ignore embedded commands.\n
- Capability inventory: The skill has the ability to execute internal Python scripts for validation via
subprocess.runinscripts/validate_operations_artifacts.py.\n - Sanitization: No sanitization or content validation of the task strings is performed before rendering.\n- [COMMAND_EXECUTION]: The validation script
scripts/validate_operations_artifacts.pyexecutes a local Python script using thesubprocessmodule.\n - Evidence: The script resolves a path to
../../shared/scripts/validate_artifact_types.pyand executes it to validate output formatting. This is an expected validation pattern using vendor-controlled internal resources.
Audit Metadata