review-data-pr
Perform an intelligent review of geographic data PRs beyond schema validation. Use this skill whenever reviewing a data PR, performing code review on contributions, checking if data makes geographical sense, or assessing data quality. Trigger on: PR review requests for data changes, "review this PR", "does this look right", "is this data correct", quality assessment requests, geographic plausibility checks, suspicious pattern detection, or any pull request touching files in the contributions/ directory. This goes beyond schema validation to check real-world geographic accuracy.
80
100%
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
The workflow explicitly instructs the agent to “Read the PR description” (Step 1) and to inspect the PR’s free-form text for intent/data source, which is outsider-authored content when the PR is submitted by someone other than the operating user, creating an indirect prompt-injection path into the LLM context.
- Repository
- dr5hn/countries-states-cities-database
- Commit
81d1277
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.