alterlab-labarchive
Warn
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the
labarchives-pypackage directly from a specific GitHub repository (github.com/mcmero/labarchives-py). This source is not associated with a recognized trusted organization or the skill author's own infrastructure, which introduces a potential supply chain risk if the repository were to be compromised or contain unvetted code. - [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from notebook entries, titles, and file attachments and has the capability to perform network and file system operations.
- Ingestion points: Untrusted data enters the skill context through user-supplied entry titles, HTML content, and file paths processed in
scripts/entry_operations.pyandscripts/notebook_operations.py. - Boundary markers: The instructions and scripts do not implement delimiters or safety warnings to ensure the agent ignores instructions embedded within the research data it processes.
- Capability inventory: The skill utilizes the
requestslibrary for network operations (API calls and uploads) and performs file system writes for notebook backups. - Sanitization: There is no evidence of input validation, escaping, or filtering of notebook content before it is processed or sent to the LabArchives API.
Audit Metadata