run-module

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs HTTP GET requests to https://registry.nextflow.io/api/v1/modules to retrieve module metadata. This domain is the official registry for the Nextflow ecosystem, managed by the vendor nextflow-io, and is used here for legitimate search functionality.
  • [COMMAND_EXECUTION]: The skill executes nextflow module commands via the Bash tool. These commands are the native way to interact with Nextflow Registry modules and are necessary for the skill's primary purpose of running workflow components.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data from the Nextflow Registry search API.
  • Ingestion points: Module names and descriptions fetched from https://registry.nextflow.io/api/v1/modules in SKILL.md.
  • Boundary markers: Not present; the agent is instructed to process the output directly.
  • Capability inventory: Includes Bash command execution, which allows the agent to run the modules identified during the search process.
  • Sanitization: The skill uses a hardcoded Python one-liner to parse the JSON response and print specific fields, which acts as a basic filter, though it does not sanitize the text content itself. Given this is a search tool, the risk is minimal and inherent to its operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:02 PM