The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to manage the learning project environment. It uses mkdir -p to establish a specific directory structure for projects and python3 to execute a local processing script, scripts/generate_anki_cards.py. These operations are transparently documented and align with the skill's primary objective of organizing and processing study data.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes untrusted external content, such as user-uploaded documents and web articles, to generate study materials.
Ingestion points: Raw resources stored in projects/<主题名称>/0-resources/ are used as the source for all subsequent note and card generation steps.
Boundary markers: The templates (e.g., templates/2-notes.md) do not implement explicit delimiters or instructions to ignore potential commands embedded within the source materials.
Capability inventory: The agent has the capability to read files, write new markdown files to the local filesystem, and execute a Python script for TSV conversion.
Sanitization: There is no evidence of input validation or sanitization to filter out malicious instructions hidden within the processed study resources.

learning-master