Skill audit report

Seedance 2.0 Skill OS audit report.

A modular agent skill package for directing Seedance 2.0 filmmaking workflows across text, image, video, audio, references, safety rewrites, and production handoff.

REVIEWED · REVIEWNeeds reviewGenerated Jun 16, 2026Heuristic metadata audit
83
Audit
82
Trust
88
Quality
70
Security
96
Maintain
78
Install

OpenAgentSkill Trust Score

83
Strong shortlist

Stars, maintenance, license, docs, install safety, permission surface, and installability.

The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

INFO

76

796 GitHub stars

Stars/forks activity

INFO

71

796 stars, 155 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

1d since push

License clarity

PASS

86

MIT

README/SKILL.md completeness

PASS

100

Metadata includes enough usage and workflow context

Dependency/runtime risk

INFO

72

command execution surface

Install availability

PASS

92

python scripts/install_codex_skill.py --force

Install command safety

PASS

92

simple repository or package install path

Permission surface

INFO

76

shell or command execution

Repository evidence

PASS

86

https://github.com/Emily2040/seedance-2.0

Review status

INFO

88

AI review data available

Checks

Install and adoption review

3 passed · 2 review

Author-published GitHub skill

PASS

README and SKILL.md present

PASS

Recent maintenance

PASS

Guarded local installer uses shutil.rmtree with --force

INFO

Warnings

  • Installer can replace the existing local seedance-20 skill directory when --force is used. Review scripts/install_codex_skill.py before running in sensitive environments.
  • Seedance platform/API claims should be checked against the repo source-status references before production use.

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.