copywriting

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References an external GitHub repository (https://github.com/coreyhaines31/marketingskills) and suggests installing content from there. This source is a personal repository and is not a verified or well-known service provider.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided marketing copy for rewriting, creating a surface for indirect instructions.
  • Ingestion points: User-supplied text provided for copywriting tasks (triggered by SKILL.md frontmatter).
  • Boundary markers: Absent; there are no instructions to the agent to treat input as data rather than instructions.
  • Capability inventory: No tools or executable scripts are defined in this skill file, limiting the potential impact of an injection.
  • Sanitization: None detected; the skill does not include instructions for filtering or escaping user input.
  • [NO_CODE]: The skill contains no executable scripts, configurations, or commands within the provided file, acting primarily as a discovery mechanism for an upstream repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:01 AM