tavily-cli

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation provides an installation command that fetches a shell script from the official vendor domain and executes it via bash (curl -fsSL https://cli.tavily.com/install.sh | bash).
  • [EXTERNAL_DOWNLOADS]: Users are instructed to install the tavily-cli package using standard package managers like pip or uv.
  • [COMMAND_EXECUTION]: The skill is configured to allow the execution of the tvly CLI tool for performing web searches, content extraction, and research.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external web content, which presents a surface for indirect prompt injection.
  • Ingestion points: Web content is ingested via the search, extract, map, and crawl commands in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions defined to treat fetched content as untrusted data.
  • Capability inventory: The skill allows the execution of the tvly binary, which can be used to further fetch or process remote content.
  • Sanitization: Fetched content is returned for processing without explicit sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 12:10 AM
Security Audit — agent-trust-hub — tavily-cli