generate-course-materials

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill invokes the exercode-problem CLI tool via bunx to validate course materials. This tool is a domain-specific utility provided by the @exercode/problem-utils package.
  • [COMMAND_EXECUTION]: The skill runs a validation command (bunx exercode-problem validate-course) on the local directory where materials were generated. The command uses paths managed by the agent and does not incorporate unvalidated external arguments into the shell command.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided course requirements to generate content. Ingestion points: User parameters (topic, audience) and outline approval. Boundary markers: Generated content is structured in markdown files with YAML frontmatter. Capability inventory: File system write operations and execution of the exercode-problem validation tool. Sanitization: The skill performs structural and semantic validation of all generated content using the validate-course command before finalizing the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:02 AM
Security Audit — agent-trust-hub — generate-course-materials