odyssey4me/code-review
Review PRs, MRs, and Gerrit changes with focus on security, maintainability, and architectural fit. Leverages github, gitlab, or gerrit skills based on repository context. Use when asked to review my code, check this PR, review a pull request, look at a merge request, review a patchset, or provide code review feedback.
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly fetches and ingests PR/MR/Gerrit change metadata and diffs from external code hosts (see Step 2 and Step 4: e.g., skills/github/scripts/github.py prs view, skills/gitlab/scripts/gitlab.py mrs view, gh pr diff / glab mr diff), so untrusted user-generated content from GitHub/GitLab/Gerrit will be read and can directly influence review actions and postings.
Where we found it
github.com
domain · 7 sites
The workflow fetches PR metadata, CI status, and diffs from GitHub via github.py and gh CLI, ingesting untrusted user-generated content (PR titles, descriptions, code diffs) that could contain prompt injection payloads.
gitlab.com
domain · 7 sites
The workflow fetches MR metadata, pipeline status, and diffs from GitLab via gitlab.py and glab CLI, ingesting untrusted user-generated content that could contain prompt injection payloads.
gerrit (user-configured instance)
domain · 3 sites
The workflow fetches Gerrit change metadata and diffs via gerrit.py and git diff, ingesting untrusted user-generated content from a Gerrit instance that could contain prompt injection payloads.
SKILL.md
152
If `.gitreview` file exists -> use the **gerrit** skill
SKILL.md
171
skills/gerrit/scripts/gerrit.py changes view <change-number>
SKILL.md
196
git diff HEAD~1
- Audited
- Security analysis