copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external repository (
github.com/coreyhaines31/marketingskills) and provides instructions for the user to manually install supplementary bundles. This is an informational reference and does not involve automated remote code execution. - [INDIRECT_PROMPT_INJECTION]: The skill serves as a surface for potential indirect prompt injection as it is designed to process and rewrite marketing copy provided by the user or external sources.
- Ingestion points: Marketing copy for landing pages, homepages, and ads provided during runtime (SKILL.md).
- Boundary markers: None present in the provided instructions.
- Capability inventory: None (the skill file does not define tools or executable scripts).
- Sanitization: None observed in the provided text.
- [NO_CODE]: The skill consists entirely of metadata, triggers, and documentation. It contains no executable scripts, shell commands (other than a manual 'open' instruction), or logic that runs within the agent's execution environment.
Audit Metadata