run-module

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute Nextflow CLI commands such as search, view, and run for bioinformatics data processing.
  • [EXTERNAL_DOWNLOADS]: The skill fetches module definitions and container configurations from the official Nextflow Registry (registry.nextflow.io) and Seqera Wave services.
  • [REMOTE_CODE_EXECUTION]: Running nextflow module run involves downloading and executing remote module code natively within the user's Nextflow environment.
  • [PROMPT_INJECTION]: The skill instructs the agent to ingest and summarize stdout from module execution to determine subsequent actions, which establishes an indirect prompt injection surface. Evidence: 1. Ingestion points: stdout from run and view commands in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Bash tool for shell command execution in SKILL.md. 4. Sanitization: Absent; the skill directs the agent to substitute user-provided values directly into command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 12:41 PM
Security Audit — agent-trust-hub — run-module