Skill audit report
MovieChat Audit report.
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
OpenAgentSkill Trust Score
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
705 GitHub stars
Stars/forks activity
INFO65
705 stars, 44 forks; issue activity unavailable in current metadata
Recent maintenance
FAIL38
2y since push
License clarity
PASS86
BSD-3-Clause
README/SKILL.md completeness
PASS90
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO72
credential or environment access
Install availability
PASS92
npx skills add wenhaochai/MovieChat
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN60
secrets or environment access, filesystem or document access
Repository evidence
PASS86
https://github.com/wenhaochai/MovieChat
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install and adoption review
Install path
92
npx skills add wenhaochai/MovieChat
Repository
88
https://github.com/wenhaochai/MovieChat
License
86
BSD-3-Clause
Maintenance
38
2y since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
90
Usable description available
Dependency risk
72
credential or environment access
Install command safety
92
standard package or runtime install path
Permission surface
60
secrets or environment access, filesystem or document access
Stars/forks activity
65
705 stars, 44 forks; issue activity unavailable in current metadata
Adoption
88
705 GitHub stars
Warnings
- Permission surface may require sandboxing
- Repository appears stale
- Repository looks stale
- Quality score needs review
- Permission surface needs review: secrets or environment access, filesystem or document access
- Recent maintenance: 2y since push
- Permission surface: secrets or environment access, filesystem or document access
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.
Compare nearby options