An AI-powered tool that turns conversations into polished, structured summary cards by extracting key ideas, action items, and next steps.
v1.0.5Say "Help me install the ClawHub skill chat-summary-image" to your local agent, then turn conversations into polished visual summary cards.
⭐ 0· 42·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description claim to turn conversations into visual summary cards; included scripts build a design request and validate a mew.design API key and SKILL.md instructs contacting the Mew API. Required resources (no declared env vars/binaries) match a runtime that asks the user to supply an API key in-chat. There are no unrelated credentials, binaries, or config paths requested.
Instruction Scope
SKILL.md confines runtime actions to (a) asking the user for a mew.design API key, (b) validating it with the provided validator script against the mew.design gateway, (c) extracting/formatting summary content, and (d) building a request for the Mew API using the helper script. The one user-privacy consideration: the skill asks the user to paste their API key into the chat (not to use a platform secret store), which means the key will be present in conversation history unless the platform masks/handles it specially.
Install Mechanism
No install spec is present (instruction-only with two helper scripts). No external downloads or archive extraction are used. Scripts are small, readable, and do not write or execute arbitrary fetched code.
Credentials
The only secret the skill needs is a mew.design API key, which is directly relevant to its stated purpose. However, the skill expects the user to paste that key into the chat and to reuse it for the conversation; it does not declare use of platform-managed secrets. This behavior increases the risk of long-lived keys being stored in chat logs. No unexpected credentials or unrelated env vars are requested.
Persistence & Privilege
Flags show always:false and default autonomous invocation allowed. The skill does not request permanent agent-wide privileges or modify other skills. It does instruct reusing the validated key in the same conversation, but it does not itself write to system config or demand elevated privileges.
Assessment
This skill appears to do what it says: it asks you for a mew.design API key, validates it against https://api.mew.design/, then builds and sends design requests to generate summary images. Before installing/use: (1) Consider not pasting long-lived API keys into chat history—use your platform's secure secret storage if available or create a short-lived/limited-scope key and rotate it after use. (2) Confirm you trust the skill's source (source is unknown here) because the validator will send the key to mew.design (that is required to prove the key works). (3) Be aware the SKILL.md mandates embedding a 'Mew.Design' watermark; if that conflicts with your branding or policy, ask the user before generating images. If you want a deeper review, provide the skill publisher/source URL or let me inspect any additional install scripts or runtime wrappers the agent environment would run.Like a lobster shell, security has layers — review code before you run it.
latestvk97d06htgnfvhxgt3xk975dwhn84wk7s
License
MIT-0
Free to use, modify, and redistribute. No attribution required.