cross-app-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and contains no executable code or scripts.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it is designed to process external, untrusted content.\n
  • Ingestion points: The workflow reads data from emails, attachments, and files using tools like 'himalaya' and 'excel-analyzer' (see SKILL.md).\n
  • Boundary markers: There are no explicit delimiters or instructions within the orchestration logic to isolate untrusted data from the agent's core instructions.\n
  • Capability inventory: The skill coordinates tools with significant capabilities, including file system access and email transmission.\n
  • Sanitization: The instructions do not define any sanitization or validation steps for the data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:19 PM