ai-seo-2

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes a Python runner script (scripts/run.py) to communicate with the vendor's official API at ai-skills.ai. This is a standard and expected architectural pattern for this type of service.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its data-processing nature:
  • Ingestion points: The skill ingests untrusted data through the materialText, materialUrl, and materialFile parameters defined in references/form-schema.json.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded directives are used in the prompt templates.
  • Capability inventory: The scripts/run.py script includes network capabilities (urllib.request) to transmit data to the vendor's backend.
  • Sanitization: No evidence of sanitization or content filtering for the input data was found in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — ai-seo-2