charmkeeper-integration-tests
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill references code and configuration from Canonical repositories (e.g., conftest.py, renovate.json). Canonical is not on the explicitly trusted whitelist, but the references are used as templates for integration testing, aligning with the skill's primary purpose.
- [COMMAND_EXECUTION] (LOW): The skill executes a local setup script
scripts/create-charmkeeper-vm.shand usesmultipass exec. This is expected behavior for an integration testing skill. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected. The skill reads repository-provided test files and executes them via
toxin a VM. Malicious test files could attempt to exploit the agent's context. 1. Ingestion points: Local repository files intests/integration. 2. Boundary markers: Absent. 3. Capability inventory:multipass exec,tox,scripts/create-charmkeeper-vm.sh. 4. Sanitization: Absent.
Audit Metadata