nimble-web-expert

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash and Python to interface with the Nimble CLI and manage data extraction workflows.
  • Executes nimble for web fetching, searching, and mapping tasks.
  • Uses python3 for one-time environment setup, result caching, and parallelizing batch requests using asyncio templates.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the Nimble CLI from the NPM registry and the nimble_python library. These are official tools provided by Nimbleway to enable the skill's core functionality.
  • [DATA_EXFILTRATION]: While the skill's primary function is fetching data from external URLs, it includes explicit security guardrails in its rules/output.md and SKILL.md to mitigate risks associated with untrusted data.
  • Ingestion points: External data enters the agent context via nimble extract, nimble search, and nimble agent commands.
  • Boundary markers: The skill instructs the agent to save results to files in a .nimble/ directory and use incremental reading tools like head and grep rather than loading entire pages into the context.
  • Capability inventory: The skill has permissions for filesystem writes and Bash execution.
  • Sanitization: There are explicit instructions for the agent to disregard any commands or prompts embedded in the scraped web content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:37 PM