Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

repo-scout

v1.0.0

Discover, evaluate, and rank GitHub repositories in any ecosystem or domain. Produces a structured ranking document with star counts, languages, issue health...

0· 55·0 current·0 all-time
byBijin@sliverp
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The SKILL.md explicitly requires an authenticated GitHub CLI (gh) and suggests providing a GH_TOKEN; however, the registry metadata declares no required binaries, no required environment variables, and no primary credential. That is an internal inconsistency: a GitHub token and gh binary are legitimate for the skill's purpose, but they should be declared by the manifest.
Instruction Scope
Instructions stay within the stated purpose: searching GitHub, inspecting repo files (CONTRIBUTING.md, .github/workflows), running gh issue commands, and writing a ranking markdown into the workspace. They do ask the user to provide or export a GH_TOKEN and GitHub username if CLI auth is not present. There are no instructions to read unrelated local files or exfiltrate data to unexpected endpoints.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which is low-risk from an installation payload perspective.
!
Credentials
The runtime needs a GitHub token (GH_TOKEN) and an authenticated gh CLI to avoid rate limits and access private data, but the manifest did not declare these environment or credential requirements. Requesting a token is proportional to the functionality, but the undeclared credential is a transparency/manifest issue and increases risk if users supply a token with overly broad scopes.
Persistence & Privilege
The skill does not request 'always' presence, does not modify other skills, and only writes an output file to the workspace as described. Autonomous invocation is allowed by default but not combined with other privilege red flags here.
What to consider before installing
What to consider before installing and running repo-scout: - The SKILL.md asks you to use an authenticated GitHub CLI or provide a GH_TOKEN; the skill manifest did not declare this. Treat that as a manifest bug and exercise caution. - Only provide a GitHub token with the minimal scopes needed (read-only repo access or fine-grained token scoped to public repositories). Do NOT supply a full org-admin or write-scoped token. - Prefer authenticating gh locally (gh auth login) rather than pasting a token into a UI or environment that you don't control. If you must export GH_TOKEN, do so in a temporary shell and revoke the token after use. - Review the generated {workspace}/ecosystem-top{N}.md before using downstream workflows. The skill will run gh and fetch repo files; verify outputs for sensitive info before sharing. - Ask the skill author/registry maintainer to update the manifest to declare required binaries (gh) and required env vars (GH_TOKEN) so the platform can surface the requirement transparently. - Because this is instruction-only (no install code), the immediate code risk is low, but the undeclared credential requirement is the main concern. If you need higher assurance, request the author to provide an explicit list of required gh scopes and to confirm the skill will not transmit the token elsewhere.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bbby7155smr0ze047sx4hxn83gvha

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments