support-toolkit
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists primarily of markdown documentation and templates designed to guide an AI agent in setting up customer support platforms. No malicious patterns were identified across any analyzed files.
- [COMMAND_EXECUTION]: The skill includes a local Python script (
scripts/check-output.py) used to validate the presence of required sections in generated deliverables. This script uses standard libraries (pathlib,sys) and performs simple string matching on local files without any network access or dynamic execution of untrusted input. - [DATA_EXFILTRATION]: No network operations, credential harvesting, or access to sensitive local file paths (e.g.,
.ssh,.aws,.env) were found. References to external services like Intercom, Zendesk, and Plain are limited to configuration guidance and official platform documentation. - [PROMPT_INJECTION]: The instructions focus on structured delivery of support platform guides. There are no attempts to override agent safety filters, bypass instructions, or extract system prompts.
Audit Metadata