The Agent Skills Directory

Indirect Prompt Injection Surface: The skill processes user-provided content (outlines, notes, casebooks) and stored data to generate study materials. This attack surface is a security consideration because instructions embedded in source materials could influence the generated output. However, this is expected behavior for the skill's primary purpose. 1. Ingestion points: Processes user-provided source text and configuration files (CLAUDE.md) in the plugin's configuration directory. 2. Boundary markers: No explicit delimiters or 'ignore embedded instruction' warnings are used during the ingestion of external source data. 3. Capability inventory: The skill is capable of writing study-related data and session history to files within its designated directory (~/.claude/plugins/config/law-student/). 4. Sanitization: No explicit sanitization or strict schema validation for ingested text was identified.
Persistent Data Storage: The skill maintains study progress and flashcard data by writing to the local file system. This persistence mechanism is used for the legitimate purpose of tracking study sessions and card buckets between user interactions.

flashcards