tavily-hikari-search

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the tvly-hikari command-line interface to perform web searches and manage configuration.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the open web.
  • Ingestion points: Results returned by the tvly-hikari search command in SKILL.md.
  • Boundary markers: None; the instructions do not include specific delimiters or warnings to ignore instructions embedded within the search results.
  • Capability inventory: Shell command execution via the tvly-hikari tool.
  • Sanitization: None; the skill instructs the agent to summarize the JSON result directly without validation or filtering.
  • [SAFE]: The skill promotes secure handling of credentials by using a configuration command (tvly-hikari configure) rather than requiring raw API keys or hardcoded tokens.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 04:21 PM
Security Audit — agent-trust-hub — tavily-hikari-search