course-builder
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local utility script
scripts/verify.shthat is executed to perform quality assurance on curriculum files. The script uses standard system utilities likegrep,find, andsedto verify instructional design best practices. - [PROMPT_INJECTION]: The skill processes user-provided course topics and existing workspace documentation, creating an indirect prompt injection surface. This ingestion is necessary for the skill's primary function of curriculum generation and alignment.
- Ingestion points: Processes user interview data for course goals and reads learner profiles from the
02-DOCS/wiki/teaching/directory. - Boundary markers: No explicit delimiters are defined for user-provided data.
- Capability inventory: Access to local file systems for reading/writing curriculum docs and command execution via
verify.sh. - Sanitization: No explicit sanitization of input data is described, relying on standard agent guardrails.
Audit Metadata