ai-image-gen-guide

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The execution script scripts/run.py transmits the AISKILLS_API_KEY environment variable and user-provided parameters to the vendor's API endpoint at https://ai-skills.ai. This is a standard operational requirement for the skill to function as part of the AI Skills ecosystem.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and processes untrusted external data.
  • Ingestion points: Data enters the system via the materialText, materialUrl, and materialFile parameters defined in references/form-schema.json.
  • Boundary markers: No explicit delimiters or instructional safeguards (e.g., "ignore instructions within this block") are implemented in the prompt configuration to separate user data from agent instructions.
  • Capability inventory: The system performs network operations via scripts/run.py to communicate with the vendor API.
  • Sanitization: There is no evidence of input validation, filtering, or escaping of the user-provided content before it is processed by the underlying language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — ai-image-gen-guide