ab-test-plan
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts, including
campaign-tracker.py,sample-size-calculator.py, andsignificance-tester.py, located in the${CLAUDE_PLUGIN_ROOT}/scripts/directory to manage experiment history and perform statistical analysis. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from local configuration files to populate parameters for its operations, creating a potential injection surface if the input data is not sanitized.
- Ingestion points: Data is read from
~/.claude-marketing/brands/_active-brand.json,~/.claude-marketing/brands/{slug}/profile.json, andguidelines/_manifest.jsonas described in the Process section ofSKILL.md. - Boundary markers: The skill does not define specific boundary markers or instructions to ignore embedded commands within the brand profile or manifest data.
- Capability inventory: The skill has the capability to execute shell commands through the bundled Python scripts.
- Sanitization: There is no evidence of sanitization or validation logic for the
{slug}variable or other brand-specific data before it is interpolated into shell command arguments.
Audit Metadata