filmcraft-jcut-dialogue
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and associated data files (JSON/Markdown) define a legitimate video editing workflow. No malicious patterns such as prompt injection, persistence, or privilege escalation were detected. The skill primarily coordinates the invocation of the FilmCraft CLI with validated parameters.
- [EXTERNAL_DOWNLOADS]: The skill references technical documentation from the official KDE Kdenlive GitHub repository to verify editing methodologies. These references target a well-known, trusted organization and are informational in nature, posing no threat of unauthorized remote code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a data ingestion surface by processing external media files (AVI, WAV). However, the attack surface is limited to technical metadata extraction (probes for framerates, durations, and timestamps). The instructions emphasize technical validation of the media before processing, which serves as a mitigation against content-based injection attacks.
Audit Metadata