creator-launch
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional and focused on generating static Markdown files for user review. It does not include any executable code, scripts, or external dependencies.
- [DATA_EXPOSURE]: The skill contains explicit guardrails to prevent data exposure, instructing the agent to keep personal data (emails) out of files and repositories and to use the creator's existing tools instead.
- [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or system modifications. The skill explicitly limits its own capabilities by stating it must not post, send, schedule, or charge.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted data (follower comments and DMs) to populate drafts, it has low risk as the output is intended for human review and manual publishing. The skill provides clear instructions to use placeholders like
[OPEN]for missing information rather than hallucinating details.
Audit Metadata