ai-ecommerce-search
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses a provided Python runner script (
scripts/run.py) to communicate with its backend API atai-skills.ai. It correctly handles authentication by requiring an API key (AISKILLS_API_KEY) to be set in the environment, avoiding hardcoded credentials. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core functionality of analyzing untrusted external data.
- Ingestion points: Data enters the context through the
materialText,materialFile, andmaterialUrlparameters as defined inreferences/form-schema.json. - Boundary markers: No explicit delimiters or instructions are provided in the skill's prompts to isolate analyzed content from the agent's instructions.
- Capability inventory: Across all files, the skill does not have the capability to execute system commands, modify the local file system, or perform unauthorized network operations.
- Sanitization: No sanitization or validation of the input materials is performed by the client-side skill instructions or scripts.
Audit Metadata