labarchive-integration
Warn
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires downloading and installing a Python package (
labarchives-py) from a personal GitHub repository (https://github.com/mcmero/labarchives-py). This source is not associated with a verified organization or the official vendor, posing a potential supply chain risk. - [REMOTE_CODE_EXECUTION]: The recommended installation method (
pip install git+https://github.com/mcmero/labarchives-py) involves downloading and executing code (setup scripts) from an unverified external repository. - [COMMAND_EXECUTION]: The skill uses Python scripts to perform local file system operations, including creating configuration files (
config.yaml), creating backup directories, and writing notebook data downloaded from the API to the disk. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from external API responses and local files without proper sanitization or boundary markers.
- Ingestion points: API responses from LabArchives in
scripts/notebook_operations.pyand local file reads for uploads inscripts/entry_operations.py. - Boundary markers: No boundary markers or 'ignore' instructions are used when processing external data in scripts or prompts.
- Capability inventory: Includes file system write access for backups and network access via the
requestslibrary across multiple scripts. - Sanitization: No sanitization or validation is performed on the data fetched from the API or read from local files before processing.
Audit Metadata