The Agent Skills Directory

[SAFE]: The skill operates entirely within its defined scope of capturing and formatting educational notes. No malicious patterns, unauthorized network access, or credential harvesting techniques were identified.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user (the 'learner-voiced summary') and external 'primary source links'.
Ingestion points: User-provided summary in SKILL.md (via 'learner's voice' rule) and source links in assets/cornell-template.md.
Boundary markers: The skill lacks explicit sanitization or delimiters for user-provided summaries, which are directly written to Markdown files.
Capability inventory: The skill has the capability to write files to the .ai/learning/ directory and interact with the spaced-recall skill.
Sanitization: No specific sanitization or validation of the user input or source links is performed.
Note: This is considered a common pattern for note-taking applications and poses minimal risk in this specific context.

cornell-notes