tavily-hikari-extract
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
tvly-hikariCLI tool to perform content extraction from specified URLs via the shell. - [EXTERNAL_DOWNLOADS]: The skill initiates network requests to a configured Hikari API endpoint (
/api/tavily/extract) to retrieve and process external web content. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external URLs, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: External URL content extracted by
tvly-hikariand returned to the agent (SKILL.md). - Boundary markers: None explicitly defined in the workflow instructions.
- Capability inventory: Execution of
tvly-hikarivia shell commands (SKILL.md). - Sanitization: Not specified; the skill relies on the upstream Hikari facade and agent-level safety filters.
Audit Metadata