The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install Python packages from an external Git repository: https://github.com/ShengLin1001/myalloy_package.git. This repository is owned by the skill author and serves as a companion library for the documented software.
[COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands to perform its core functions, including pip install for dependency management, sphinx for documentation building, compileall for verification, and git for repository synchronization and deployment.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes data from external repositories (source code and documentation requirements) and executes commands based on that content.
Ingestion points: The agent reads and processes Python source code (via Sphinx autodoc) and dependency lists (docs/requirements.txt) from the user's repository.
Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from following malicious instructions potentially embedded in the processed repository files.
Capability inventory: The skill possesses the ability to execute arbitrary shell commands via pip and git, write files to the local system, and push changes to remote GitHub repositories.
Sanitization: No sanitization or validation of the ingested repository content is performed before it is processed by the build tools.

p-page-creator