Skills
skills/allinherog-star/ai-skills/ai-image-generation/Gen Agent Trust Hub

ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The script scripts/run.py transmits user-provided data including image goals, audience descriptions, and material content to the vendor's API at https://ai-skills.ai. This behavior is the primary function of the skill and occurs over a secure connection to the developer's official domain.
  • [PROMPT_INJECTION]: The skill processes untrusted input from parameters such as materialText and external content retrieved via materialUrl. This presents a surface for indirect prompt injection (Category 8).
  • Ingestion points: User-provided strings and external URLs defined in SKILL.md and references/form-schema.json are interpolated into the API request.
  • Boundary markers: The documentation does not specify the use of delimiters or specific instructions for the model to ignore embedded commands in the input data.
  • Capability inventory: The skill possesses network communication capabilities via scripts/run.py to interact with the AI Skills backend.
  • Sanitization: Static analysis does not reveal specific input validation or sanitization logic within the provided runner script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — ai-image-generation