gh-modify-pr

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

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.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

The agent may make lasting local code changes and create a commit; remote changes should only happen if you approve a push.

Why it was flagged

The skill instructs the agent to modify tracked code and create a local commit, with remote push gated on user approval. This is expected for the stated purpose, but users should notice that it can change their working tree and repository history.

Skill content

`git add <files>`
   - `git commit -m "<clear message>"`
11. Push only if user asks/approves:
   - `git push`

Recommendation

Review the diff and commit before approving any push, especially on shared or protected branches.

NoteHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

The skill can access repositories and PR comments available to your configured GitHub credentials.

Why it was flagged

The workflow relies on the user's GitHub CLI and SSH/git authentication to read PR data and clone repositories. This is purpose-aligned, but it uses the user's existing account privileges.

Skill content

`gh api repos/<owner>/<repo>/pulls/<number>/comments`
...
`git clone git@github.com:<owner>/<repo>.git`

Recommendation

Use it only with a GitHub account and SSH credentials that have the repository access you intend, and avoid running it in repositories where the agent should not make edits.