tavily-map
Fail
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documentation provides an installation command that downloads a shell script from 'https://cli.tavily.com/install.sh' and pipes it directly to bash. This resource is hosted on the official domain of the skill author (tavily-ai).
- [COMMAND_EXECUTION]: The skill requires access to the 'Bash' tool to execute 'tvly' commands for mapping website structures and discovering URLs.
- [PROMPT_INJECTION]: The skill processes untrusted data from external websites in the form of URL paths and domains, which constitutes an indirect prompt injection surface.
- Ingestion points: Output from the 'tvly map' command containing external URLs (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the command examples.
- Capability inventory: The skill uses 'Bash(tvly *)' to interact with the environment (SKILL.md).
- Sanitization: There is no evidence of sanitization or filtering of the discovered URL data before it is returned to the agent context.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.tavily.com/install.sh - DO NOT USE without thorough review
Audit Metadata