The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands and Python scripts to manage the user's learning progress.\n
It uses subprocess.run() in scripts/finish_problem.py to perform Git operations such as adding files and committing changes. These calls are implemented securely using argument lists.\n
The scripts/git_ops.sh script facilitates the synchronization of the local practice environment with a remote Git repository via git push.\n
The references/normal_mode_sop.md instructs the agent to execute user-written Python solutions using the python3 command to verify them against test cases.\n- [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection due to its core functionality of reading and analyzing user-provided code.\n
Ingestion points: The agent ingests untrusted data when reading user-written solution files as defined in references/normal_mode_sop.md.\n
Boundary markers: No explicit delimiters are used to separate user-provided code from the agent's instructions during analysis.\n
Capability inventory: The skill possesses the capability to write files to disk, execute shell commands through subprocess.run (in scripts/finish_problem.py), and interact with network services via Git operations (in scripts/git_ops.sh).\n
Sanitization: The skill does not perform sanitization or validation on user-provided content before processing or execution.

leetcode-teacher