director-frame-gen
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Connects to the api.kie.ai endpoint to initiate image generation tasks and monitor their progress. This is a legitimate integration with a well-known AI service provider.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it incorporates untrusted user data into its operations.
- Ingestion points: Processes user-provided scene.prompt and sceneImageUrl values from SKILL.md.
- Boundary markers: Lacks delimiters to separate user data from the skill's instructions.
- Capability inventory: Makes network requests to an external API using an environment-stored API key.
- Sanitization: No input validation or sanitization steps are documented for the user-controlled fields.
Audit Metadata