sc-edit
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (studio.py and splicecraft.py) using shell commands to perform video processing tasks like joining, tracking, and rendering. It also uses shell redirection to log files for debugging.
- [INDIRECT_PROMPT_INJECTION]: The agent is directed to read and trust user-provided script files (e.g., SKRIP-, naskah) as the definitive source for video editing parameters.
- Ingestion points: Reads various text and markdown files (SKRIP-, BACA-, naskah*, script*) from the project directory (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to separate the untrusted script content from the agent's logic.
- Capability inventory: The agent has the ability to execute shell commands and read/write to the local file system.
- Sanitization: While the tools include a 'lint' step to check for word consistency, there is no sanitization applied to the script content before the agent interprets it to plan the video cards.
Audit Metadata