marketingskills-ai-agents

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and installs content from an external GitHub repository coreyhaines31/marketingskills using npx, git clone, and git submodule (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided product details to create a context.md file that influences all subsequent marketing agent actions. Ingestion points: User input collected during the 'Create my product marketing context' command (SKILL.md). Boundary markers: None provided in instructions to prevent the agent from following embedded instructions in the product description. Capability inventory: File writing (.agents/skills/), code generation, and site auditing. Sanitization: No validation or escaping of user input is specified.
  • [DYNAMIC_EXECUTION]: The skill generates functional code for A/B testing, programmatic SEO, and metadata schemas using predefined templates and user context (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 08:31 PM
Security Audit — agent-trust-hub — marketingskills-ai-agents