The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads content from /docs/course-description.md to perform quality scoring and analysis. This represents an ingestion point for untrusted data that could influence agent behavior.
Ingestion points: The agent reads the existing /docs/course-description.md file in the Analysis Workflow (Step 2.1).
Boundary markers: The instructions do not define explicit boundary markers or ignore-rules for the content being read.
Capability inventory: The skill writes new assessment reports, modifies file metadata, and alters the mkdocs.yml configuration file.
Sanitization: There is no explicit sanitization or verification of the content within the course description file before it is processed for scoring.
[COMMAND_EXECUTION]: The skill performs standard filesystem operations to maintain project structure and documentation.
Evidence: The instructions include creating directories via mkdir -p docs/learning-graph and updating the nav section of mkdocs.yml. These actions are consistent with the skill's stated purpose, and the configuration change is gated by a user confirmation step.

course-description-analyzer