valyu-best-practices

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a CLI wrapper (scripts/valyu) and a Node.js implementation (scripts/valyu.mjs) that provide a command-line interface for interacting with Valyu API endpoints such as Search, Answer, and Deep Research.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions by retrieving content from various external sources (web, academic journals, news, and financial filings). This establishes a vulnerability surface where the agent could ingest malicious instructions embedded within the retrieved data.
  • Ingestion points: The search, contents, answer, and deepResearch functions retrieve untrusted external content into the agent's context.
  • Capability inventory: The skill has network access to the Valyu API (api.valyu.ai) and performs local file operations to store configuration in ~/.valyu/config.json.
  • Sanitization: The provided scripts and instructions do not include specific sanitization logic or prompt boundary markers to mitigate the risks of processing third-party content.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the vendor's official SDKs via standard package managers (npm install valyu-js, pip install valyu) and references community-maintained integrations from GitHub. These resources are standard for API toolkits.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:57 PM
Security Audit — agent-trust-hub — valyu-best-practices