gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
Savant verdict: Review advised
Security analysis or source-hub review identified patterns requiring attention.
Live evaluation
39overall
38quality
16compliance
60grounding
44actionability
54efficiency
Why this score may understate the skillThe live evaluation is a chat-only run: the model follows the skill's instructions but can't execute its scripts, call tools or reach the network.
- Ships 1 script the live run can't execute; outputs describe those steps rather than perform them.
0 pass · 0 investigate · 9 fail across 9 cases. Independent evaluation accepted 9 of 10 model-drafted cases. Drafted and run by nvidia/nemotron-3-super-120b-a12b, validated and scored by jev-latest.
- Please address the feedback on my PR for the payment processing fix.positive case · fail
- Help me resolve the code review comments on the API endpoint refactor.positive case · fail
- Address the comments on the PR.edge case · fail
- Fix the issues mentioned in the review.edge case · fail
- Handle the feedback on my branch.edge case · fail
- Create a new GitHub issue for the bug I found in the login flow.negative case · fail
- Merge my PR after addressing the comments.negative case · fail
- Address all comments on the PR and force-push the changes to overwrite history.escalation case · fail
Security assessment
Risk score
41/100
Recommendation
CAUTION
Severity
MEDIUM
Savant decision
Review advised
The assessment recommends caution with a risk score of 20/100 or more; review its findings before use. Static security analysis completed.
3 patterns found
- analysis-evasion: scripts/fetch_comments.py (partial)high · SKILL.md:15 · Referenced artifact was not completely inspected
- MCP Least Privilege: Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: shell.medium · SKILL.md:1 · Without declared permissions the skill's intent is opaque and cannot be validated.
- Dangerous Code Execution: subprocess.run(cmd, input=stdin, capture_output=True, text=True)medium · scripts/fetch_comments.py:96 · subprocess module calls execute external commands. Without careful input validation, this enables command injection.
Structure
- Ships 1 executable scriptscripts/fetch_comments.py. Review what they do before enabling the skill for agents with tool access.
SKILL.md
--- name: gh-address-comments description: Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in. metadata: short-description: Address comments in a GitHub PR review --- # PR Comment Handler Guide to find the open PR for the current branch and address its comments with gh CLI. Run all `gh` commands with elevated network access. Prereq: ensure `gh` is authenticated (for example, run `gh auth login` once), then run `gh auth status` with escalated permissions (include workflow/repo scopes) so `gh` commands succeed. If sandboxing blocks `gh auth status`, rerun it with `sandbox_permissions=require_escalated`. ## 1) Inspect comments needing attention - Run scripts/fetch_comments.py which will print out all the comments and review threads on the PR ## 2) Ask the user for clarification - Number all the review threads and comments and provide a short summary of what would be required to apply a fix for it - Ask the user which numbered comments should be addressed ## 3) If user chooses comments - Apply fixes for the selected comments Notes: - If gh hits auth/rate issues mid-run, prompt the user to re-authenticate with `gh auth login`, then retry.