content-creator
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests that the user or agent can optionally add a third-party plugin from the marketplace (
coreyhaines31/marketingskills) to access more content templates. - [DATA_EXFILTRATION]: To align content with the brand voice, the skill reads local project files such as
.agents/SYSTEM/ARCHITECTURE.mdandREADME.md. No instructions were found that exfiltrate this data to external servers. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project documentation and previous posts as context for its generation tasks.
- Ingestion points: Project files in
.agents/SYSTEM/and existing newsletter/social media archives. - Boundary markers: Absent from the instructions.
- Capability inventory: None detected. The skill instructions are limited to text analysis and generation, with no subprocess, shell, or network capabilities provided in the skill scripts.
- Sanitization: Absent.
Audit Metadata