perplexity-local-dev-loop

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill correctly instructs users to store API keys in .env.local and includes it in a list of git-ignored files. This is a standard and recommended practice for secret management.
  • [EXTERNAL_DOWNLOADS]: The skill references standard development tools and libraries like openai, vitest, and tsx. These are well-known packages in the Node.js ecosystem.
  • [COMMAND_EXECUTION]: The skill provides standard npm/pnpm scripts for local development and testing (e.g., vitest, tsx watch). These commands are typical for the described workflow and do not perform unexpected actions.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The scripts provided are for local execution of user-controlled code.
  • [PROMPT_INJECTION]: The skill contains no instructions that attempt to override AI safety guidelines or bypass constraints. It focuses entirely on technical environment setup.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 09:39 PM
Security Audit — agent-trust-hub — perplexity-local-dev-loop