cube-spin
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local JavaScript file (~/.claude/skills/video-effects/run.cjs) using Node.js. This execution is the primary mechanism for the skill's video processing functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes user-supplied MP4 files.
- Ingestion points: The skill reads an external media file provided by the user (e.g.,
my-clip.mp4). - Boundary markers: There are no explicit instructions or delimiters provided to the agent to ignore potential instructions embedded within the video content or metadata.
- Capability inventory: The skill has the capability to execute shell commands via
nodeand perform file system read/write operations for video rendering. - Sanitization: There is no evidence of sanitization or validation performed on the input media content before it is processed by the underlying engine.
Audit Metadata