op55-compose
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as video timelines, narration scripts, and analysis JSON files. This creates an ingestion surface for indirect prompt injection; however, the skill's instructions strictly constrain the output to structured music metadata and deterministic code generation.
- Ingestion points: Video timelines, narration timestamps, and analysis metadata.
- Boundary markers: Not explicitly defined in the prompt interpolation.
- Capability inventory: Writes .mjs and .md files to the local file system and executes a local rendering script.
- Sanitization: Not explicitly defined for input strings.
- [DYNAMIC_EXECUTION]: The skill's primary purpose is to generate a JavaScript module (
score.mjs) based on user-provided parameters and predefined templates. This generated code is subsequently executed by a local tool (render.mjs). This behavior is the intended functional core of the skill and does not involve the execution of untrusted remote code. - [COMMAND_EXECUTION]: The skill uses the shell to execute a local rendering command (
node render.mjs). The execution path is controlled via a variable provided by a related skill, maintaining a scoped execution environment within the developer's local workspace.
Audit Metadata