content-creator
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised of documentation and persona-based instructions. It does not contain any executable scripts, binaries, or system-level commands.\n- [EXTERNAL_DOWNLOADS]: The skill mentions an external resource ('coreyhaines31/marketingskills') in its documentation. This is a manual reference for the user and is not an automated download or execution task.\n- [PROMPT_INJECTION]: The skill retrieves brand context by reading local project files such as '.agents/SYSTEM/ARCHITECTURE.md' and 'README.md'. This exposes an indirect prompt injection surface where instructions in those files could influence the agent's output. However, since the skill has no code execution capabilities, the risk is negligible.\n
- Ingestion points: 'references/full-guide.md' (Step 1 and Step 2 instructions for reading project files).\n
- Boundary markers: Absent; the skill does not instruct the agent to use delimiters for external data.\n
- Capability inventory: The skill defines no executable code, tools, or shell access.\n
- Sanitization: Absent.
Audit Metadata