newsletter-creator
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses role-playing and instructional frameworks that are entirely focused on newsletter editing and strategy. There are no attempts to override agent safety protocols, extract system prompts, or bypass behavioral constraints.
- [DATA_EXFILTRATION]: The skill does not perform any network operations, access sensitive file paths, or request credentials. It functions as a text generation assistant for creative content.
- [COMMAND_EXECUTION]: No unauthorized or dangerous shell commands were detected. The skill references platform-specific tools like 'create_post' for legitimate drafting purposes within the intended environment.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts at runtime. The installation instructions in the README follow standard practices for the platform.
- [OBFUSCATION]: All content in SKILL.md and README.md is in plain, readable Markdown. No hidden characters, encoded URLs, or steganographic techniques were found.
Audit Metadata