The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the labarchives-py package from a third-party GitHub repository (github.com/mcmero/labarchives-py). This repository is not an official LabArchives source nor a verified vendor, posing a supply-chain risk as the code is executed locally.
[COMMAND_EXECUTION]: Several bundled scripts (scripts/notebook_operations.py, scripts/entry_operations.py) are designed to execute shell commands and perform network requests to interact with the LabArchives API. These scripts depend on the external, unverified labarchivespy module.
[CREDENTIALS_UNSAFE]: The skill's setup process involves collecting and storing sensitive institutional Access Keys and user passwords in a local config.yaml file. While the setup script attempts to set restrictive file permissions (0600), managing high-value secrets in plain-text configuration files presents a risk of credential exposure if the local environment is compromised.
[PROMPT_INJECTION]: The skill provides instructions for the agent to process notebook data, which creates a surface for indirect prompt injection. Malicious content stored within a lab notebook could potentially influence agent behavior when the agent reads or summarizes notebook entries.

labarchive-integration