perplexity-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill follows secure credential management practices by instructing users to access the
PERPLEXITY_API_KEYthrough environment variables (process.env.PERPLEXITY_API_KEYandos.environ["PERPLEXITY_API_KEY"]) rather than hardcoding secrets. - [EXTERNAL_DOWNLOADS]: The skill depends on the well-known
openaipackage for both Node.js and Python implementations, which is a standard industry library for interacting with AI completion services. - [INDIRECT_PROMPT_INJECTION]: The implementation provides functions that ingest user-defined queries. While this represents a surface for untrusted data, the skill is designed for information retrieval and display, and does not include logic that would execute actions based on the retrieved content, maintaining a safe posture.
Audit Metadata