marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's metadata and usage instructions reference an external GitHub repository (
https://github.com/coreyhaines31/marketingskills) for the full assets and scripts. It encourages the manual installation of code from this untrusted personal repository. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze marketing copy, hooks, and framing, which involves processing external text. This creates a surface where malicious instructions embedded in the copy could influence the agent's behavior.
- Ingestion points: User-provided marketing copy, hooks, and presentation text described in SKILL.md.
- Boundary markers: Absent. The instructions do not specify delimiters or guidelines to ignore embedded instructions within the analyzed copy.
- Capability inventory: None. The skill file contains no local scripts, automated tool invocations, or file system write operations.
- Sanitization: Absent. The skill does not define any methods for filtering or validating external text inputs.
- [NO_CODE]: The skill file is composed entirely of markdown documentation and YAML frontmatter. It lacks any executable code, scripts, or automated command sequences.
Audit Metadata