johnnie-to-staging
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration files for an AI agent. It contains no executable scripts (Python, Node.js, etc.) or system commands.
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs in
references/source-notes.md. These are links to well-known and reputable film industry and academic websites, including Lancaster University's research repository (eprints.lancs.ac.uk), the official Festival de Cannes website (festival-cannes.com), and established film journals (sensesofcinema.com,filmcomment.com). These references are used solely for informational purposes to cite the director's public staging principles. - [PROMPT_INJECTION]: The skill includes clear boundaries in
SKILL.mdthat explicitly instruct the AI to use public-source-inspired directing principles and avoid impersonation or claims of private access. There are no patterns of behavior override or safety bypass instructions. - [DATA_EXFILTRATION]: There are no network operations, API calls, or attempts to access sensitive local files. The skill operates entirely within the provided instructional context.
Audit Metadata