canvas-week-plan
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a vulnerability surface by ingesting and processing untrusted data from an external source (Canvas LMS).
- Ingestion points: The skill retrieves assignment names, descriptions, and instructions using the
get_my_upcoming_assignmentsandget_assignment_detailsMCP tools in SKILL.md. - Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings when processing assignment content retrieved from the external API.
- Capability inventory: No high-risk capabilities such as file system writes, subprocess execution, shell commands, or network exfiltration were detected in the skill's instructions or metadata.
- Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the data retrieved from the Canvas environment.
Audit Metadata