GitHub Smart Code Digest

AdvisoryAudited by VirusTotal on Apr 16, 2026.

Overview

Type: OpenClaw Skill Name: github-smart-code-digest Version: 1.0.0 The skill bundle provides a legitimate workflow for automating GitHub code reviews and publishing summaries to Feishu Wiki. It utilizes the GitHub CLI (`gh`) in workflow.json to fetch PR data and diffs, processes them via an AI review engine, and uses a card renderer for visualization. No evidence of malicious intent, data exfiltration, or unauthorized command execution was found; the use of shell commands and environment variables for API keys is consistent with its stated purpose.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Note

ASI03: Identity and Privilege Abuse

What this means

The skill can read PR and commit data available to the logged-in GitHub account and write pages to the configured Feishu Wiki space.

Why it was flagged

The skill needs the user's GitHub authenticated CLI context and Feishu app credentials with write access to publish reports.

Skill content

GitHub CLI (`gh`) 已安装并完成 `gh auth login`; 飞书 App 具备 Wiki 写入权限; `FEISHU_APP_ID`、`FEISHU_APP_SECRET`

Recommendation

Use a least-privilege GitHub account/token and a Feishu app limited to the intended Wiki space; remove or rotate credentials when no longer needed.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Actual GitHub access, AI review, rendering, and Feishu publishing behavior also depends on those separately installed skills.

Why it was flagged

The combo depends on additional skills that are not included or version-pinned in the provided artifacts.

Skill content

openclaw install github
openclaw install code-review-skill
openclaw install card-renderer
openclaw install feishu-wiki

Recommendation

Review and install trusted versions of the dependency skills before enabling this workflow, especially in private repositories.

Note

ASI02: Tool Misuse and Exploitation

What this means

This is expected for GitHub automation, but unsafe parameter handling by the runtime could cause command errors or unintended shell behavior.

Why it was flagged

The workflow uses shell command templates with interpolated repository and PR parameters.

Skill content

'list_prs': 'gh pr list --repo ${repo} ...'; 'get_diff': 'gh pr diff ${pr_number} --repo ${repo} > /tmp/pr_${pr_number}.diff'

Recommendation

Only use validated repository names and dates, and prefer runtimes that pass arguments safely rather than concatenating shell strings.

Note

ASI07: Insecure Inter-Agent Communication

What this means

Private code changes and review findings may be processed by several components and then become visible in the selected Feishu Wiki space.

Why it was flagged

PR diffs and review outputs are passed through multiple skills before being published to Feishu.

Skill content

github → code-review-skill → card-renderer → feishu-wiki; inputs include `diff_files`: `/tmp/pr_*.diff` and `review_data`: `/tmp/digest_reviews.json`

Recommendation

Confirm the data-handling behavior of each dependent skill and publish only to restricted Feishu spaces appropriate for the repository sensitivity.

Note

ASI10: Rogue Agents

What this means

If enabled, reports can continue to be generated and posted on a schedule without a manual trigger each time.

Why it was flagged

The skill supports persistent scheduled execution and repeated creation of Wiki report pages.

Skill content

定时自动推送（推荐） ... `openclaw cron add` ... 飞书 Wiki 每次运行会创建新页面（历史报告保留）

Recommendation

Enable cron only for intended repositories and spaces, monitor generated pages, and remove the schedule when it is no longer needed.