playbook-ai-content-workflow
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of static Markdown instructions and prompt templates. No executable scripts, binary files, or dangerous shell commands are included in the package.
- [PROMPT_INJECTION]: While the skill uses sophisticated prompting techniques (Role, Context, Task, Constraints, Output), these are used for their intended purpose of content generation and brand alignment. There are no patterns indicating attempts to bypass AI safety guidelines or extract system instructions.
- [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive system files. All data processing involves the user providing non-sensitive brand information into templates.
- [EXTERNAL_DOWNLOADS]: The skill mentions various well-known AI services (such as ChatGPT, Claude, and Canva) as recommendations for the user but does not perform any automated downloads or background network requests to these or any other services.
- [COMMAND_EXECUTION]: There are no instances of shell command execution, subprocess calls, or system-level modifications.
Audit Metadata