@tank/hook-creator
Pass
Audited by Gen Agent Trust Hub on May 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation provides technical templates for executing shell commands using the
ctx.$API within agent lifecycle hooks. - Evidence: Examples in
references/worked-examples.mddemonstrate the use of shell execution for retrieving git differences and running code formatters. - [DATA_EXFILTRATION]: The skill requests broad read access to the local filesystem (
**/*) in its configuration. - Evidence: The
tank.jsonmanifest declaresfilesystem: { "read": ["**/*"] }, which is intended to allow the agent to assist in analyzing project structure for hook creation. - [EXTERNAL_DOWNLOADS]: The documentation references various external development tools and formatters.
- Evidence:
references/worked-examples.mdsuggests the use of standard packages and tools such asprettier,black, andgofmtfor automated formatting tasks.
Audit Metadata