Family Memory Timeline
v1.0.0自动分析家庭照片和对话，生成结构化时间线故事，帮助回顾和珍藏家庭重要记忆。
⭐ 0· 78·0 current·0 all-time
byhaidong@harrylabsj
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the code: handler implements emotion analysis, timeline building, chapter/story generation from media paths and conversation text. No unrelated credentials, binaries, or external services are requested. The declared 'no external dependencies / simulated implementation' aligns with the provided source files.
Instruction Scope
SKILL.md asks the user to provide media paths (including examples of absolute/local paths) and conversation text, which is appropriate for this purpose. The included code treats media as metadata (path, description) and does not read files or access the filesystem or external APIs. However, the examples and phrasing could be interpreted to mean the agent should gather local files — the skill itself does not include instructions to read arbitrary system files, but a deploying agent or user could choose to supply file contents or have the agent collect them. Users should be cautious about giving the agent broad filesystem access when using this skill.
Install Mechanism
No install specification is provided (instruction-only / included source files). There are code files bundled, but no external downloads, package installs, or extract-from-URL steps. package.json exists but lists no dependencies. This is low risk from an install perspective.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The code does not read environment variables or attempt to access credentials. The absence of requested secrets is proportional to the described functionality.
Persistence & Privilege
Skill flags are default (always:false, agent invocation enabled). It does not request persistent presence or modify other skills/system settings. Autonomous invocation is allowed by platform default; combined with the lack of credentials and network calls, this does not materially increase risk for this skill.
Assessment
The skill appears to do what it says: synthesize stories from media metadata and conversation text using a simulated analysis engine. Before installing or using it: (1) review the repository (clawhub.json/skill.json point to a GitHub repo) to confirm source authenticity; (2) do not pass sensitive files or system-wide paths unless you trust the running agent—the skill expects media paths but the included code does not itself read files; if an agent collects files for you it may read arbitrary local data; (3) test the skill in a sandbox with non-sensitive sample data (scripts/test-stub.js is provided for this); (4) confirm the deployment environment prevents unwanted filesystem/network access if you expect strict privacy. Overall this skill is internally coherent and low-risk given the provided sources, but exercise normal caution when giving any agent access to local files or when supplying actual family photos/conversations.Like a lobster shell, security has layers — review code before you run it.
latestvk9767r12sjsg6mqxgvyp9h4a0n84bvcb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.