Skills
skills/allinherog-star/ai-skills/kling-3-0/Gen Agent Trust Hub

kling-3-0

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python runner script (scripts/run.py) that users are instructed to execute locally. This script handles communication with the AI Skills API.
  • [DATA_EXFILTRATION]: The provided runner script transmits parameters and the AISKILLS_API_KEY to the service endpoint at https://ai-skills.ai. This is the intended behavior for interacting with the vendor's infrastructure.
  • [PROMPT_INJECTION]: The skill accepts external content through several input fields, creating a potential surface for indirect prompt injection:
  • Ingestion points: materialText, materialUrl, and materialFile fields defined in references/form-schema.json.
  • Boundary markers: None identified in the provided prompt configuration.
  • Capability inventory: The scripts/run.py script performs network requests to the ai-skills.ai domain.
  • Sanitization: No explicit sanitization or filtering logic is present in the skill's local configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:58 AM
Security Audit — agent-trust-hub — kling-3-0