302ai-api-integration
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute a Python script (
scripts/parse_api_list.py) via the bash command line to process and filter API information. - [EXTERNAL_DOWNLOADS]: The skill fetches data from remote sources, specifically documentation and API lists from the
doc.302.aidomain using theWebFetchtool. - [PROMPT_INJECTION]: The skill processes untrusted external data from API documentation which introduces a surface for indirect prompt injection. Ingestion points: External documentation pages and the
llms.txtfile retrieved fromhttps://doc.302.ai/. Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the fetched documentation. Capability inventory: The skill can execute shell commands, perform network requests, and generate source code in various programming languages. Sanitization: No evidence of content validation or sanitization for the retrieved documentation is present in the skill instructions.
Audit Metadata