marketing-growth-experiment
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references methodology from a public GitHub repository (github.com/coreyhaines31/marketingskills) for attribution purposes. This is an informational link and does not involve remote code execution or automated downloads.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied marketing goals and experiment ideas. While it lacks explicit boundary markers for this input, the skill does not possess capabilities for file system access, shell command execution, or network communication, which significantly limits the risk of data poisoning or multi-step chain attacks.
- [REMOTE_CODE_EXECUTION]: It references internal post-processing tools (moai-coworker:ai-slop-reviewer and moai-writer:korean-humanize). These follow the vendor's naming conventions for internal helper agents and are used for refining output prose rather than executing arbitrary scripts.
Audit Metadata