office-automation

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because its primary function involves processing untrusted external documents.
  • Ingestion points: The skill reads and interprets content from local files including Word documents, Excel spreadsheets, and email templates (e.g., 员工名单.xlsx, 邮件模板.txt).
  • Boundary markers: The instructions do not define clear delimiters or provided specific directives for the agent to ignore instructions embedded within the data files it processes.
  • Capability inventory: The agent has the ability to write to the local file system, generate reports, and send emails via SMTP, which could be misused if a document contains adversarial instructions.
  • Sanitization: There is no mention of content filtering, sanitization, or validation for the data ingested from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:42 PM
Security Audit — agent-trust-hub — office-automation