canvas-morning-check
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from the Canvas LMS, which could be used to influence agent behavior through indirect prompt injection.\n
- Ingestion points: External data enters the agent context via the
list_assignments,list_submissions, andget_student_analyticstools defined inSKILL.md.\n - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when the agent processes or reports on the ingested Canvas data.\n
- Capability inventory: The skill includes the
send_conversationtool, which allows the agent to take write actions (sending messages) based on the results of the ingested data.\n - Sanitization: There is no evidence of sanitization or validation of the content retrieved from Canvas before it is used in the agent's prompts or follow-up actions.
Audit Metadata