morning-check

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified through the processing of untrusted student and course data.
  • Ingestion points: The skill ingests assignment titles, student submission details, and grades via the list_assignments and list_submissions tools within the SKILL.md file.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within the fetched data are present in the processing steps.
  • Capability inventory: The agent has the capability to generate formatted reports and send student communications via the send_conversation tool.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved data before it is used to populate report templates or draft messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 01:20 PM