Agent skill · Audited from source
Review Pr
skill · desplega-ai/agent-swarmMIT licenceAudited 14 Oct 2026 · source 4df377778267
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 4df377778267 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback
Cite
Cite this page
ModelsAtlas. “Review Pr (desplega-ai/agent-swarm)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/desplega-ai/review-pr
5 skills are called “Review Pr”. You are viewing desplega-ai/agent-swarm.
- desplega-ai/agent-swarm★ 882!CAUTION
- tirth8205/code-review-graph★ 32k✓SAFE
- FlorianBruniaux/claude-code-ultimate-guide★ 6.1k!CAUTION
- mikeyobrien/ralph-orchestrator★ 3.2k✓SAFE
- fcakyon/claude-codex-settings★ 1.2k✓SAFE
Trust audit
Audit 0.4.1 · source read 14 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 5 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (5)
MEDIUMInventory / provenanceinv.symlink · .agents/skills/dashboard-ui
.agents/skills/dashboard-ui
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .agents/skills/swarm-local-e2e
.agents/skills/swarm-local-e2e
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .claude/skills/dashboard-ui
.claude/skills/dashboard-ui
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · .claude/skills/swarm-local-e2e
.claude/skills/swarm-local-e2e
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · AGENTS.md
AGENTS.md
- Why
- link not followed
- Fix
- —
Audit 0.4.1 · source sha 4df377778267 · 14 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherdesplega-ai GitHub organizationOwner of the repository this skill is read from
- Source folderdesplega-ai/agent-swarm/plugin/pi-skills/review-prThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict4df377778267A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback
---
name: review-pr
description: Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback
---
# Review Pull Request / Merge Request
Review a PR (GitHub) or MR (GitLab) by analyzing changes and providing structured feedback.
**Provider detection:** Check the remote URL or provided URL:
- If GitHub → use `gh pr` commands
- If GitLab → use `glab mr` commands
## Arguments
- `pr-number-or-url`: Either a PR number (e.g., `123`) or a full URL
## Workflow
### 1. Setup
- Ensure the repo is cloned to `/workspace/personal/<repo-name>` (clone with `gh repo clone` if needed)
- Fetch, checkout the PR branch, get PR details and diff
### 2. Check CI Status (MANDATORY)
Check CI with `gh pr checks <pr-number>` (or `glab mr view --json pipelines`).
**If CI checks are failing, this is an automatic REQUEST_CHANGES.** Do not approve a PR with failing CI. Include the failing check names and error details in your review.
### 2b. Review Repository Guidelines
Check the "Review Guidance" section of your Repository Guidelines for repo-specific review instructions (e.g., "check README.md", "enforce camelCase in specific directories"). Apply these instructions during your review below.
Also note the repo's **Merge Policy** — check `allowMerge` and `mergeChecks` before approving or merging. If `allowMerge` is false, do NOT merge — only review and approve/request changes.
### 3. Verify Tests Are Included (MANDATORY)
Check that the PR includes test changes. **If the PR modifies code but does not add or update tests, this is an automatic REQUEST_CHANGES.** Every code change must include corresponding tests.
Exceptions:
- Pure documentation changes (README, comments only)
- Configuration-only changes (CI config, linter config, env files)
- Dependency version bumps with no code changes
When requesting changes for missing tests, be specific about what tests are needed.
### 4. Analyze the Changes
Review the diff for:
- **Security issues**: SQL injection, XSS, command injection, secrets in code
- **Logic errors**: Off-by-one errors, null handling, edge cases
- **Performance concerns**: N+1 queries, unnecessary loops, memory leaks
- **Code quality**: Naming, complexity, duplication, missing error handling
- **Test coverage**: Are included tests sufficient? Do they cover edge cases?
Also consider running the test suite locally and checking for TypeScript errors.
### 5. Post the Review
Post your review with a verdict: APPROVE, REQUEST_CHANGES, or COMMENT.
```bash
gh pr review <pr-number> --approve --body "Review message"
gh pr review <pr-number> --request-changes --body "Review message"
gh pr review <pr-number> --comment --body "Review message"
```
### 6. Post Inline Comments on Specific Lines
For detailed feedback on specific lines, use the GitHub API:
```bash
# Get the commit SHA
COMMIT_SHA=$(gh pr view <pr-number> --json headRefOid --jq '.headRefOid')
# Post an inline comment
gh api repos/<owner>/<repo>/pulls/<pr-number>/comments \
--method POST \
-f commit_id="$COMMIT_SHA" \
-f path="src/path/to/file.ts" \
-f line=42 \
-f side="RIGHT" \
-f body="Your inline comment here."
```
**Parameters:**
- `commit_id`: PR head commit SHA
- `path`: Relative file path
- `line`: Line number in the diff
- `side`: `"RIGHT"` for new code (additions), `"LEFT"` for removed code
- `body`: Comment text (supports markdown)
### 7. Re-reviewing After Changes
When the author pushes updates:
1. Fetch latest and re-checkout the PR
2. Check if previous concerns were addressed
3. Reply to existing comment threads:
```bash
gh api repos/<owner>/<repo>/pulls/<pr-number>/comments/<comment-id>/replies \
--method POST \
-f body="Thanks, this looks good now!"
```
4. Update your review status (approve or request further changes)
## Tips
- Focus on substantive issues over style nitpicks
- Acknowledge good work when you see it
- Having the repo cloned allows you to run tests and verify changes locallyExcerpt, first 3,990 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 4df3777
git clone https://github.com/desplega-ai/agent-swarm git -C agent-swarm checkout 4df377778267
The author documents no install command, so this uses the repository directly. Our verdict covers commit 4df377778267 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
4df377778267
Similar skills
All automation skills →desplega-ai/agent-swarm
Close a GitHub or GitLab issue with a summary comment
desplega-ai/agent-swarm
Create a pull request (GitHub) or merge request (GitLab) from the current branch
desplega-ai/agent-swarm
Implement a GitHub issue or GitLab issue and create a PR/MR
desplega-ai/agent-swarm
Investigate and triage a Sentry error issue
desplega-ai/agent-swarm
Respond to a GitHub issue/PR or GitLab issue/MR
desplega-ai/agent-swarm
Start the Agent Swarm Leader
Questions about Review Pr
What does the Review Pr skill do?
Is Review Pr safe to install?
What can Review Pr access on my machine?
How current is this page?
Sources
- github.com/desplega-ai/agent-swarm/tree/main/plugin/pi-skills/re — the audited source at commit 4df377778267 and every finding aboveObserved · 14 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Review Pr skill do?
- Is Review Pr safe to install?
- What can Review Pr access on my machine?