Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Fetch the latest AI daily brief from imjuya/juya-ai-daily (GitHub) and return the Overview (summary) section.
v1.0.0Fetch the latest AI daily brief from imjuya/juya-ai-daily (GitHub) and return the Overview (summary) section.
⭐ 0· 161·1 current·1 all-time
byHaoxuan Ma@hunter-wrynn
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description match the instructions: the script lists BACKUP/*.md in imjuya/juya-ai-daily and extracts the '## 概览' section. That capability does not require credentials for public repos and is appropriate for the stated purpose. However, the SKILL.md's runtime commands use additional binaries (node, awk, sed, basename, etc.) beyond the single declared dependency (curl), creating an inconsistency between claimed requirements and actual runtime needs.
Instruction Scope
The instructions confine themselves to calling the GitHub API and downloading a public markdown file, then extracting the overview section. They conditionally read GITHUB_TOKEN or GH_TOKEN to increase rate limits (optional), and they print the latest date to stderr. The script does not instruct reading arbitrary host files or posting data to third-party endpoints beyond api.github.com and raw file download URLs. Still, the instructions run an embedded node -e script and several shell utilities that are not declared; that mismatch could cause runtime surprises.
Install Mechanism
This is instruction-only (no install spec, no code files). That is the lowest-risk install mechanism: nothing is downloaded or written by the registry/install process itself. The runtime will invoke curl and other tools already present on the host.
Credentials
The metadata declares no required environment variables, but the SKILL.md conditionally reads GITHUB_TOKEN and GH_TOKEN if present. Asking for optional GitHub tokens to raise rate limits is reasonable, but the skill metadata should declare these as optional env vars. More importantly, if a user provides a token, it grants GitHub API access — the token should be scoped and limited. The script will accept any token present in the environment, so users should not set broad-scoped or long-lived tokens without understanding the risk.
Persistence & Privilege
The skill is not always-enabled, it does not request persistent system presence, and it does not modify other skills' configurations. Autonomous invocation is enabled by default (normal) but not itself a red flag here.
What to consider before installing
This skill appears to do what it says (fetch a public GitHub markdown and extract the 'Overview'), but there are a few mismatches you should address before installing or running it unattended:
- The SKILL.md uses node (node -e), awk, sed, basename and other shell utilities but the registry metadata only lists curl. Ensure your agent environment actually provides these binaries or update the metadata. If you cannot provide node, the script will fail or behave unexpectedly.
- The script will read GITHUB_TOKEN or GH_TOKEN from the environment if present. If you supply a token to avoid rate limits, use a narrowly scoped, short-lived GitHub token (or avoid setting one). Do not set broad-scoped personal tokens in an environment accessible to untrusted skills.
- Because the skill downloads and prints content from a public repo, it will surface whatever text is in those markdown files. That content could include arbitrary text or links; review returned content before acting on it.
- If you want to proceed, either (1) run the provided commands manually once to verify output and that no unexpected binaries are invoked, or (2) update the skill metadata to declare 'node' and other required tools and list optional env vars (GITHUB_TOKEN/GH_TOKEN) so the requirements match the instructions.
Given these mismatches (undeclared runtime binaries and undeclared optional env vars), I rate the package as suspicious rather than clearly benign. If the owner updates the metadata to explicitly list node and the optional env vars, this would likely be downgraded to benign.Like a lobster shell, security has layers — review code before you run it.
latestvk973bk3waacrm5v1hqc2d3r43n8323pr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🗞️ Clawdis
Binscurl
