wan-2-7
Generate Wan 2.7 Videos on RunComfy
Teams need a repeatable way to create short Wan 2.7 videos without rebuilding CLI arguments. This skill explains setup, inputs, prompt patterns, and safer RunComfy invocation choices.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "wan-2-7" from https://skillstore.io/skills/doany-ai-wan-2-7.md and its manifest at https://skillstore.io/api/skills/doany-ai-wan-2-7/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 "wan-2-7". Request: Create a short product showcase video for a premium skincare bottle.
Expected outcome:
A polished Wan 2.7 prompt with camera motion, studio lighting, duration, aspect ratio, and negative prompt guidance.
Using "wan-2-7". Request: Make a vertical lip-synced founder message from a supplied voiceover.
Expected outcome:
A generation plan that checks audio length, recommends 9:16 framing, and describes stable camera and lighting choices.
Using "wan-2-7". Request: Decide whether Wan 2.7 is the right model for a fast concept test.
Expected outcome:
A concise routing recommendation that compares model strengths, speed needs, audio needs, and output limits.
Security Audit
Medium RiskMost static alerts are false positives from Markdown backticks, field names, and example fences. Confirmed risks remain because the skill intentionally uses local CLI commands, package installation, and RunComfy network submission. No evidence found of prompt injection, covert malware behavior, or system reconnaissance in SKILL.md.
Confirmed security concerns (1)
Capability review items (10)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
โ๏ธ External commands (39)
๐ Network access (5)
๐ Filesystem access (3)
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-wan-2-7/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-wan-2-7?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-wan-2-7?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-wan-2-7/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-wan-2-7.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). wan-2-7 security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-wan-2-7/audits/4BibTeX citation
@techreport{doany-ai-doany-ai-wan-2-7-2026,
author = {doany-ai},
title = {wan-2-7 security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-wan-2-7/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: "wan-2-7 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-wan-2-7/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-wan-2-7: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-wan-2-7
2026-09-09
prime-skills-wan-2-7
2026-11-01
doany-ai-wan-2-7
2026-09-09
agentspace-so-wan-2-7
2026-10-22
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Create Lip-Synced Ads
Build short product or spokesperson clips that use a supplied audio track for lip-sync timing.
Produce Dub Variants
Reuse a core scene prompt with different audio URLs for language or market variants.
Prototype Motion Prompts
Test camera moves, aspect ratios, prompt expansion, and seed choices before a final production run.
Try These Prompts
Create a five-second Wan 2.7 video prompt for [product or scene]. Use 16:9, 1080p, and one clear camera movement.
Plan a vertical Wan 2.7 clip for [platform]. Include aspect ratio, duration, motion, negative prompt guidance, and likely output limits.
Prepare a lip-synced spokesperson request for Wan 2.7 using my audio URL: [URL]. Check duration, format, aspect ratio, and prompt clarity.
Compare Wan 2.7 with HappyHorse, Seedance, Kling, and LTX for this video goal: [goal]. Recommend the best route and explain tradeoffs.
Best Practices
- Use one primary action per clip so motion remains clear.
- Confirm audio length, format, and file size before using lip-sync.
- Review the exact command and output directory before running the CLI.
Avoid
- Do not include secrets, private media URLs, or unreleased campaign details in prompts.
- Do not ask for many unrelated actions in one short clip.
- Do not rely on vague negative prompts such as poor quality or bad colors.