trello-api
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill requires the installation of the 'py-trello' library via pip. This is a well-known, legitimate package for Trello API interaction. No suspicious or unversioned remote execution patterns were found.
- PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted data from Trello (card descriptions, labels, board names).
- Ingestion points: Data enters the context through 'client.list_boards()', 'board.get_list()', and card attribute access in README.md.
- Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are present in the documentation snippets.
- Capability inventory: The skill can perform network operations (create cards, modify boards, set up webhooks) via the Trello API.
- Sanitization: No sanitization or validation of external Trello content is demonstrated in the provided examples.
- FALSE POSITIVE (SAFE): An automated scan flagged 'label.name' as a malicious URL. This is a false positive; 'label.name' is a standard property access in Python/JavaScript for retrieving the name attribute of a Trello label object and is not a functional URL.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata