canvas
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a standard read-only interface for fetching course and assignment data from the Canvas LMS API. The implementation uses established libraries and follows expected patterns for API interaction without evidence of malicious intent, obfuscation, or unauthorized access.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for external data, which is a common vector for indirect prompt injection.
- Ingestion points: External course and assignment data is retrieved from the Canvas API using
requests.getinscripts/canvas_api.py. - Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded commands within the fetched data.
- Capability inventory: The script is restricted to performing network GET requests and does not have capabilities to write files or execute commands based on the external content.
- Sanitization: The skill truncates assignment descriptions to 500 characters, which serves as a basic mitigation against large injection payloads.
Audit Metadata