ab-test-plan

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes python campaign-tracker.py and scripts/sample-size-calculator.py. These commands use arguments, such as {slug}, which are sourced from local JSON files in the ~/.claude-marketing/ directory.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection vulnerability surface. Ingestion points: Data is read from ~/.claude-marketing/brands/ (profiles and guidelines) and campaign history logs. Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing logic. Capability inventory: The skill has the ability to execute shell commands and write detailed experiment specifications. Sanitization: There is no evidence of validation or escaping for data used in command execution or prompt construction.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 11:41 PM