reels-script-writer
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content such as transcripts, ideas, and core materials to generate video scripts. This ingestion of untrusted data represents an indirect prompt injection surface. The skill includes specific mitigation instructions to separate internal metadata and vetting notes from the final script output, verify facts against original sources, and avoid using imagination to fill in missing information.
- [EXTERNAL_DOWNLOADS]: The documentation references an installation command (
npx skills add Jaycheng1103/superbrain-reels-script-writer) that fetches the skill package from the author's GitHub repository. This is a standard installation procedure for the platform and targets the vendor's own infrastructure. - [COMMAND_EXECUTION]: The README.md file provides shell commands intended for manual repository validation and evaluation by a developer, such as
./tests/validate_repo.shandpython3 tests/score_eval_results.py. These commands are not intended for automatic execution by the AI agent during typical skill invocation.
Audit Metadata