Skills/ClawHub/github-integration

github-integration@1.0.0

CAUTION· install only

Publisher claims: "Manage GitHub repositories by creating and updating issues, pull requests, files, labels, and performing code searches using GitHub REST API with a personal..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher gaolfun · publishing for 132 daysInstalls 721Last detonated 38 h ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Host or command assembled from base64 fragments; Host or command assembled from base64 fragments. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commandSKILL.md:926 · Privileged sudo command — agent may execute with elevated privilegessudo apt update && sudo apt install -y jqFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Host or command assembled from base64 fragmentsSKILL.md:476 · Host or command assembled from base64 fragments> echo "$CONTENT" | base64 -dFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File permission modification commandSKILL.md:68 · File permission modification command — agent changes file ownership/permissionschmod 600 ~/.config/openclaw/github_tokenFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Host or command assembled from base64 fragmentsSKILL.md:1006 · Host or command assembled from base64 fragmentsecho "$CONTENT" | base64 -dFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Privileged sudo commandSKILL.md:82 · Privileged sudo command — agent may execute with elevated privilegessudo apt install jq # Debian/UbuntuFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:906 · File permission modification command — agent changes file ownership/permissionschmod 600 ~/.config/openclaw/github_tokenFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:1050 · File permission modification command — agent changes file ownership/permissions- Use file-based storage with `chmod 600` as shown in §2.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Host or command assembled from base64 fragmentsSKILL.md:810 · Host or command assembled from base64 fragments-H "Authorization: Bearer ${GH_TOKEN}" | jq -r '.content' | base64 -d)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈6,828 tok
1 file · 2 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim gaolfun: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim gaolfunPropose a patch to the maintainer