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.pytransmits theAISKILLS_API_KEYenvironment variable and user-provided parameters to the vendor's API endpoint athttps://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, andmaterialFileparameters defined inreferences/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.pyto 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