portkey-python-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the official Portkey SDK and its integrations using standard package managers. Specifically, it references
portkey-ai,langchain-portkey, andllama-index-llms-portkeyavailable via PyPI. - [INDIRECT_PROMPT_INJECTION]: As a developer SDK, the skill provides a surface for processing untrusted user data which is then forwarded to LLM providers.
- Ingestion points: Data enters the system via the
messagesparameter in thechat.completions.createmethod and theinputparameter in embedding/image/audio generation methods acrossSKILL.mdandADVANCED_FEATURES.md. - Boundary markers: No specific boundary markers or instruction-ignoring delimiters are provided in the example code.
- Capability inventory: The skill facilitates network operations to LLM providers and the Portkey Gateway, and file system writes for audio/image output (e.g.,
response.stream_to_file('output.mp3')inADVANCED_FEATURES.md). - Sanitization: The provided snippets do not include explicit sanitization or validation of the input strings before they are passed to the model.
Audit Metadata