director-clip-gen

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill sends prompt details and image links to the external domain api.kie.ai. This is a necessary step for the skill's primary function of video generation.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection because the skill interpolates untrusted data into API payloads.
  • Ingestion points: Data is ingested from the character and scene prompts generated in previous pipeline steps.
  • Boundary markers: There are no delimiters or specific instructions provided to the agent to treat interpolated variables as data rather than instructions.
  • Capability inventory: The skill leverages the agent's ability to perform network operations (HTTP POST and GET) to interact with third-party APIs.
  • Sanitization: The instructions do not specify any validation or sanitization procedures for the data before it is sent to the external provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:53 AM