runcomfy-cli
Run RunComfy Models from the CLI
Creative teams and developers need a reliable way to run RunComfy models from automated terminal workflows. This skill explains authentication, schema discovery, job submission, polling, downloads, and safer scripting with the RunComfy CLI.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "runcomfy-cli" from https://skillstore.io/skills/doany-ai-runcomfy-cli.md and its manifest at https://skillstore.io/api/skills/doany-ai-runcomfy-cli/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "runcomfy-cli". User asks to generate a product image with a specific RunComfy model.
Expected outcome:
- Confirms CLI authentication status.
- Identifies required model inputs from the API tab.
- Submits the job and reports the downloaded output location.
Using "runcomfy-cli". User has a list of prompts and wants repeatable batch generation.
Expected outcome:
- Builds a batch plan with separate output folders.
- Uses safe prompt handling for each request.
- Explains retry behavior for timeout and rate-limit errors.
Using "runcomfy-cli". User needs CI usage without browser login.
Expected outcome:
- Recommends token-based authentication through a protected CI secret.
- Uses machine-readable output for downstream automation.
- Avoids logging token values or generated private URLs.
Security Audit
SafeAll 118 static matches appear to be Markdown documentation, intended RunComfy CLI examples, official RunComfy URLs, or disclosed token-storage notes. I found no prompt injection attempt, hidden exfiltration intent, or executable payload in SKILL.md; the main operational risk is normal use of an external model API with local credentials.
Risk Factors
โ๏ธ External commands (85)
๐ Network access (24)
๐ Filesystem access (5)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/doany-ai-runcomfy-cli/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-runcomfy-cli?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-runcomfy-cli?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-runcomfy-cli/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-runcomfy-cli.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
doany-ai. (2026). runcomfy-cli security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-runcomfy-cli/audits/4BibTeX citation
@techreport{doany-ai-doany-ai-runcomfy-cli-2026,
author = {doany-ai},
title = {runcomfy-cli security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-runcomfy-cli/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "runcomfy-cli security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/doany-ai-runcomfy-cli/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-runcomfy-cli:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
4 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
runcomfy-com-runcomfy-cli
2026-09-09
doany-ai-runcomfy-cli
2026-09-09
prime-skills-runcomfy-cli
2026-11-20
agentspace-so-runcomfy-cli
2026-10-22
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Automate Campaign Assets
Run repeatable image or video generation jobs from terminal workflows and save outputs into organized folders.
Batch Test Model Prompts
Submit many prompts, capture request IDs, retry transient failures, and compare generated results across models.
Run Media Jobs In CI
Use token-based authentication and machine-readable output to connect RunComfy jobs to automation pipelines.
Try These Prompts
Use the RunComfy CLI skill to verify my local setup and explain the next authentication step.
Help me run a RunComfy text-to-image model, poll until completion, and save outputs to a named folder.
Build a safe batch prompt workflow for RunComfy using a prompts file, JSON output, retries, and separate output folders.
Design an advanced RunComfy CLI pipeline that submits no-wait jobs, stores request IDs, polls later, handles retryable exit codes, and avoids token exposure.
Best Practices
- Use verified package manager installation and avoid unattended remote shell installers.
- Keep tokens in protected storage and never paste them into prompts, logs, or repositories.
- Use explicit output directories and file size expectations for automated runs.
Avoid
- Do not run model jobs with unreviewed third-party URLs unless the user supplied them for this task.
- Do not enable web search unless the task needs current real-world grounding.
- Do not mix many model schemas in one command without validating required inputs.