tavily-lead-gen
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
npx skills add tavily-ai/skills --skill <name>to install required skill dependencies. This involves executing a shell command to fetch and integrate external capabilities.\n- [DYNAMIC_EXECUTION]: By instructing the agent to dynamically add new skills at runtime, the skill introduces new instructions and potentially executable scripts into the agent's environment.\n- [EXTERNAL_DOWNLOADS]: The skill usesnpx skills addto download and install additional skill components from the author's repository.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from various external sources such as news sites and job boards.\n - Ingestion points: Web content retrieved via
tvly searchfrom numerous external domains (e.g., news sites, job boards).\n - Boundary markers: Absent; no instructions are given to the agent to treat retrieved data as untrusted or to use delimiters.\n
- Capability inventory: The agent can execute
tvlycommands and write lead data to the local file system.\n - Sanitization: Absent; no data validation or sanitization of external content is specified.
Audit Metadata