create-watch-skill
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill functions as a meta-instruction set for generating other skills. It does not contain any logic for network operations, sensitive file access, or credential harvesting.
- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters or override agent behavior. The generated output is explicitly designed to include human role definitions and action boundaries, reducing the risk of autonomous or harmful actions.
- [NO_CODE]: The skill consists entirely of instructional markdown and does not bundle any scripts, binaries, or third-party dependencies.
Audit Metadata